Operations & Delivery Perspective | 2026-09-13 SOP Draft
As of 2026-09-13, when incorporating Ego-OSCAR into the content funnel, the operations side needs an executable chain: readers enter from the paper abstract, leave with the acceptance questions corresponding to "open-source stereo plus IMU low-cost ego collection route, emphasizing a reproducible hardware stack," and receive an acceptance attachment template for E8. It likewise does not claim that TOBI holds the public benchmark itself.
Building on the task structure of Ego-OSCAR, discuss how E8 capture clips can serve long-horizon clips: contact windows, failure retention, and model-side representation of action semantics fields. Aimed at teams planning Ego datasets, VLA training, and robot transfer around 2026, emphasizing auditable delivery, versioned calibration, and hardware-synchronized quality checks, and avoiding misreading public benchmarks as any single vendor's exclusive capability.
What the Paper Timeline Tells Us
Around 2024, Ego-OSCAR pushed community discussion toward a clear question: an open-source stereo plus IMU low-cost Ego capture approach, emphasizing a reproducible hardware stack. 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 Ego-OSCAR 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 2024 and 2026 often occur across these three layers; what hardware teams should track is field/schema changes, not chasing paper titles.
For model-type tasks (this article's slug: news-seo-123-model-e8-m051), the paper timeline also indicates when "failure cases and long-tail scenarios" are incorporated into the benchmark protocol. Constraints that appear late often have more impact on VLA training than early-stage scale figures; equipment selection should reserve the ability to retain time windows before and after contact.
Dataset Boundary Statement
Ego-OSCAR and its link https://github.com/china-langhui-ego/e2-sdk in this article are in a public research context; TOBI does not claim ownership, hosting, or exclusive distribution of this dataset.

Acceptable requirements for capture hardware
Translating Ego-OSCAR's one-line claim into procurement language starts with defining "acceptable fields" rather than restating that the open-source stereo plus IMU low-cost egocentric capture approach emphasizes a reproducible hardware stack. 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 the ops team to write into an SOP (2026-09-13 version), bound to the E8 evaluation prototype:
- Freeze the E8 firmware and SDK versions; the minimal script set to reproduce the Ego-OSCAR comparison experiments.
- Bench sync testing: measure cross-path offset using LED / mechanical triggers to produce a baseline report.
- Worn-state spot check: sample 50 contact frames for multi-view consistency across scenes tagged E8, Ego-OSCAR, long-horizon clip, model.
- 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.

Mapping to TOBI E8 product capabilities
TOBI E8 targets ten-channel sensor density and expansion channels such as TOF; motion capture and R&D-grade trajectory alignment are explicit R&D goals. Procurement evaluation should distinguish "mass-production specifications" from "lab integration capabilities," and avoid misreading paper VIO baselines as fully enabled by default out of the box.
Compared with Ego-OSCAR: an open-source stereo plus IMU low-cost Ego collection route emphasizing a reproducible hardware stack. On the device side, this should be translated into clickable product fields — for example, frame rate / exposure / IMU frequency, whether on-device SLAM serves as a trajectory prior, and whether gesture / ring / wrist share the same time domain. Readers should go to /product-e8.html and /docs.html#device-sdk to verify the README and delivery package, rather than assuming the paper configuration equals the factory default.
When pillar=model and the main offering is E8, it is recommended to split "paper metrics" into Must (no purchase without them) and Stretch (R&D co-creation). Must typically covers hard synchronization, calibration versions, and recording container time semantics; Stretch may cover motion capture bridging, ten-way expansion, or cross-laboratory matrix deployment.
- E2 positioning: stereo global shutter, offline reconstruction friendly, lightweight human demo front station (can still serve as a networking secondary path when this article primarily recommends E8).
- 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·123-1) For Ego-OSCAR and E8: world-model training relies more on long-horizon consistent timelines; random cropping of short clips breaks state continuity. Under the model pillar, this directly relates to the delivery risk of "Long-horizon clip: Ego-OSCAR-insp…".
(Deep dive·123-2) For Ego-OSCAR and E8: diffusion policies are sensitive to contact phase; the data card should annotate contact_phase start and end frames. Under the model pillar, this directly relates to the delivery risk of "Long-horizon clip: Ego-OSCAR-insp…".
(Deep dive·123-3) For Ego-OSCAR and E8: Sim2Real pipelines should not use different timestamp units in sim versus real. Under the model pillar, this directly relates to the delivery risk of "Long-horizon clip: Ego-OSCAR-insp…".
(Deep dive·123-4) For Ego-OSCAR and E8: enterprise content funnel: paper page → spec page → sample unit → small-batch data → scaled procurement, with exit criteria at each step. Under the model pillar, this directly relates to the delivery risk of "Long-horizon clip: Ego-OSCAR-insp…".
(Deep Dive · 123-5) On Ego-OSCAR and E8: This article focuses on engineering acceptance field descriptions, so procurement and algorithm teams can copy them directly into RFQ attachments. Under the model pillar, this directly relates to the delivery risk of "long-duration clips: Ego-OSCAR enables...".
(Deep Dive · 123-6) For Ego-OSCAR and E8: when linking to the SDK docs, anchor to #device-sdk to keep readers from getting lost. Under the model pillar, this directly relates to the delivery risk of "Long-duration clips: Ego-OSCAR starts...".
(Deep dive·123-7) For Ego-OSCAR and E8: keeping the video poster consistent with the hero image reduces first-screen CLS and trust cost. Under the model pillar, this directly relates to the delivery risk of "Long-horizon clip: Ego-OSCAR-insp…".
(Deep dive·123-8) For Ego-OSCAR and E8: the FAQ must restate dataset boundaries to prevent sales over-promising. Under the model pillar, this directly relates to the delivery risk of "Long-horizon clip: Ego-OSCAR-insp…".
(Extension·123-B1) 2026-09-13 retrospective: there may be gaps between the E8 ten-channel and TOF channels in R&D integration versus production specifications; the contract should clearly state the delivery tier. If your team tags=E8,Ego-OSCAR,long-horizon clip,model, we recommend adding this to your project risk register.
(Extension · 123-B2) 2026-09-13 Review: Motion capture bridging is a Stretch capability and requires a separate milestone and acceptance script. If your team's tags=E8, Ego-OSCAR, long-duration clip, model, it is recommended to record this in the project risk register.
(Extended \u00b7 123-B3) 2026-09-13 retrospective: a global shutter reduces geometric distortion versus a rolling shutter in fast lateral motion scenarios, benefiting stereo matching. If your team tags=E8, Ego-OSCAR, long-duration clip, model, it is recommended to record this in the project risk register.
(Extended · 123-B4) 2026-09-13 retrospective: 65mm-level baseline selection affects depth accuracy and wearing volume, and should be consistent across the product page and data card. If your team tags=E8, Ego-OSCAR, long-duration clip, model, it is recommended to write this into the project risk register.
(Extension·123-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=E8,Ego-OSCAR,long-horizon clip,model, we recommend adding this to your project risk register.
Frequently Asked Questions (FAQ)
Q: Does TOBI provide the Ego-OSCAR dataset? No. Ego-OSCAR is a public research/community resource; TOBI only discusses specification comparison and capture hardware capabilities.
Q: Can using only E8 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-e8.webp represent? An illustrative animated image showing E8 live recording and wearing configuration; not official Ego-OSCAR release content.
Q: What attachments should I prepare when requesting a quote? It is recommended to attach https://github.com/china-langhui-ego/e2-sdk, a target hours/scene table, a Must-field checklist, and whether wrist/ring/matrix networking is required.
Next step: specification comparison and evaluation prototype
If you are planning E8,Ego-OSCAR,long-horizon clip,model scenarios against Ego-OSCAR, please contact TOBI with your Must-field checklist to apply for an E8 evaluation sample unit or a joint dataset delivery plan.
Read E8 product page, Developer Documentation · Device SDK, or Submit Quote Request and Technical Evaluation.
(Appendix · news-seo-123-model-e8-m051 · 1) When comparing against public benchmarks, only borrow the task definitions and metrics, not the data licensing boundaries. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 2) Ego-to-robot transfer should include a separate coordinate frame attachment: the transformation chain for head, wrist, world, and robot_base. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 3) If HEVC transcoding rewrites timestamps, the original_pts field must be preserved in the metadata. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 4) Ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 5) 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 on-board SLAM must not be written as an E2 factory capability. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 6) Collaborative Ego scenarios must declare the speech/instruction synchronization strategy to avoid audio-visual causal misalignment. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 7) QA spot checks should re-run the same script on a Linux host to ensure the delivery is auditable. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 8) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 9) When 60fps stereo capture is combined with a 30fps auxiliary stream, clearly specify the downsampling and phase rules. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 10) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 11) ORB-SLAM3-class VIO baselines emphasize multi-sensor timestamps; Ego devices should align to equivalent semantics. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 12) Open X-Embodiment emphasizes cross-platform action distributions; the Ego field schema should reserve an embodiment_id field. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 13) DROID-class robot data lacks human priors; E2's lightweight Ego is suitable as a pre-stage for human demonstration. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 14) The HaMeR lineage is sensitive to occlusion; ring + multi-path redundancy reduces the proportion of invisible frames. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 15) ActiveUMI demonstrates active perception; dual-channel acceptance of wrist-mounted plus head-mounted streams is the procurement-grade answer. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 16) World model training relies more on long-duration consistent timelines; random cropping of short clips destroys state continuity. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 17) Diffusion policies are sensitive to contact phase; the data card should annotate the start and end frames of contact_phase. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 18) The Sim2Real pipeline should not use different timestamp units in sim and real. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 19) Enterprise content funnel: paper page → spec page → prototype → small-batch data → scaled procurement, with exit criteria at each step. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 20) This article focuses on engineering acceptance field descriptions, so that procurement and algorithm teams can copy them directly into RFQ attachments. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 21) When linking to SDK documentation, fix the anchor to #device-sdk to reduce reader disorientation. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 22) The video poster matches the hero image, reducing first-screen CLS and trust cost. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 23) The FAQ must reiterate dataset boundaries to prevent sales from over-promising. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 24) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 25) Motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 26) Global shutter reduces geometric distortion in fast lateral motion scenarios compared to rolling shutter, benefiting stereo matching. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 27) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 28) fMP4 segments facilitate browser preview, but the training side requires a raw or lossless backup strategy. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 29) MCAP is well-suited to the ROS2 ecosystem; field naming should follow the team's schema registry. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 30) Scripts like linux_run_time_sync.sh should be versioned and cross-referenced with the firmware README. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 31) The open-source e2-sdk/e6-sdk only helps you get started; mass-production procurement still follows the commercial delivery package. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 32) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 33) Health monitoring should include camera dropout, IMU saturation, remaining storage, and thermal throttling. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 34) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 35) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 36) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 37) A VLA recipe should declare the language instruction alignment method: manual trigger vs. ASR timestamps. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 38) Human-to-robot transfer requires declaring the action space: joint vs. end-effector vs. bimanual. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 39) It is recommended that procurement contract attachments include links to public papers for task reference only, without implying data transfer. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 40) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 41) During procurement review, require the supplier to provide P50/P95 curves of sync jitter, not single-point marketing figures. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 42) In long-duration dex capture, thermal drift and bandwidth contention amplify soft alignment errors; hardware triggering is superior to pure software timestamping. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 43) Failed samples must include a timeline health score; otherwise, VLA will treat interpolated frames after repair as real contact. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 44) Cross-day capture requires declaring the time source switching strategy: whether CDC-ACM, PPS, or GNSS are mixed. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 45) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 46) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 47) DatasetServer shard limits and disk flush strategy affect whether the "last frame" is lost. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 48) 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 E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 49) When comparing against public benchmarks, only borrow the task definitions and metrics, not the data licensing boundaries. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 50) Ego-to-robot transfer should include a separate coordinate frame attachment: the transformation chain for head, wrist, world, and robot_base. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 51) If HEVC transcoding rewrites timestamps, the original_pts field must be preserved in the metadata. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 52) Ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 53) 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 on-board SLAM must not be written as an E2 factory capability. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 54) Collaborative Ego scenarios must declare the speech/instruction synchronization strategy to avoid audio-visual causal misalignment. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.
(Appendix · news-seo-123-model-e8-m051 · 55) QA spot checks should re-run the same script on a Linux host to ensure the delivery is auditable. When assessing E8 against Ego-OSCAR (2024), archive this together with the acceptance checklist dated 2026-09-13.