Back to News & Insights
Frontier Observations

Purchase E2: field gap self-check checklist for EgoLive projects

When procuring E2 for EgoLive-type tasks, include the field gap self-check, hardware synchronization, calibration version, and trajectory fields in the contract appendix, citing public papers for task reference only, without committing to dataset ownership. For teams planning around 2026

2026-09-08
Chief News Officer, TOBI Technology
Frontier Observations
Procurement E2: field gap self-check key points for the EgoLive project (174)
Chief Insights Research Frontiers 2026-09-13 Chinese original: about 5048 characters

Operations & Delivery Perspective | 2026-09-13 SOP Draft

As of 2026-09-13, when incorporating EgoLive into the content funnel, the operations side needs an executable path: readers enter from a paper abstract, leave with acceptance questions corresponding to "JoyEgoCam (a third-party capture device described in the EgoLive paper, not a TOBI product) stereo 60fps and 200Hz IMU large-scale open Ego capture specifications," and obtain an acceptance attachment template for E2. Likewise, this does not claim that TOBI holds the public benchmark itself.

When procuring E2 for EgoLive-type tasks, write the field gap self-check, hard synchronization, calibration version, and trajectory fields into the contract attachments, reference only public papers as task references, and do not commit to dataset ownership. For teams planning Ego datasets, VLA training, and robot transfer around 2026, emphasize auditable delivery, versioned calibration, and hard synchronization quality inspection, and avoid misreading public benchmarks as any single company's exclusive capability.

Live demo demo-stream
Live demo animated image (demo-stream.webp): demonstrates the E2 recording pipeline for easy comparison with EgoLive public specifications; not official material from the paper.

What the Paper Timeline Tells Us

Around 2026, EgoLive pushed the community discussion toward a clear question: the JoyEgoCam stereo 60fps and 200Hz IMU large-scale open egocentric capture specifications. The timeline tells us that the value of public benchmarks 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 solely for specification comparison and procurement language translation.

If EgoLive is included in the 2026-09-13 procurement review, three layers should be distinguished: the timing of the paper's release and open-source link, the timing of community reproduction and secondary annotation, and the timing when enterprise-built/purchased data actually enters the repository. Between these three layers, there are often method iterations from 2026 to 2026; what hardware teams should track is field/schema changes, not chasing paper titles.

For buy-type tasks (this article's slug: news-seo-174-buy-e2-b102), the paper timeline also indicates when "failure samples and long-tail scenarios" are written into the benchmark protocol. Constraints that appear later often affect VLA training more than early scale figures; device selection should reserve the ability to retain time windows before and after contact.

Dataset Boundary Statement

EgoLive and its link https://arxiv.org/abs/2604.23570 in this article are within a public research context; TOBI does not claim ownership, hosting, or exclusive distribution of this dataset.

Procurement E2: field gap self-check key points for the EgoLive project (174)
Figure 1 | Procuring E2: Key Points for the Field Gap Self-Check for the EgoLive Project (1… corresponds to E2 live hardware and wearing reference (not official EgoLive material).

Acceptable requirements for capture hardware

Translating EgoLive's one-line claim into procurement language starts with defining "acceptable fields" rather than restating the JoyEgoCam stereo 60fps and 200Hz IMU large-scale open egocentric capture specifications. 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 E2 evaluation prototype:

  1. Freeze the E2 firmware and SDK versions; reproduce the minimal script set for the EgoLive comparison experiment.
  2. Bench sync testing: measure cross-path offset using LED / mechanical triggers to produce a baseline report.
  3. Worn-state spot check: sample 50 segments for multi-view consistency of contact frames according to the E2,EgoLive,field gap self-check,procurement tag scenarios.
  4. Ingestion QC: outputs sync_health, drop_frame, and calib_version fields.
  5. Training feedback: compare contact success rates using the hard-sync subset versus the soft-alignment subset, and record the results in the procurement review.
Procurement E2: field gap self-check key points for the EgoLive project (174)
Figure 2 | Multi-view/scenario diagram used to compare EgoLive's task density and visibility assumptions.

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 EgoLive: JoyEgoCam stereo 60fps and 200Hz IMU large-scale open Ego capture specification. On the device side, this should be translated into clickable product fields — for example frame rate/exposure/IMU frequency, offline reconstruction trajectory on the computer side (E2 defaults to offline reconstruction, not on-device SLAM), and whether gestures/rings/wrist are time-synchronized in the same domain. Readers should go to /product-e2.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=buy and the primary recommendation is E2, it is advisable to split "paper metrics" into Must (no purchase without them) and Stretch (R&D co-creation). Must typically covers hardware synchronization, calibration version, and recording container time semantics; Stretch may cover motion-capture bridging, ten-stream 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.
Procurement E2: field gap self-check key points for the EgoLive project (174)
Figure 3 | The E2's appearance as shown on the product page, allowing readers to jump to /product-e2.html to verify specifications.

Engineering deep dive: turning paper metrics into gates by scenario

(Deep Dive · 174-1) Regarding EgoLive and E2: the algorithm team should specify the observation–action causal window in the data card: whether multi-channel frames are retained for 120 ms before and 200 ms after contact. Under the buy pillar, this directly relates to the delivery risk of "Procuring E2: Key Points for the Field…" for the EgoLive project.

(Deep Dive · 174-2) Regarding EgoLive and E2: during procurement review, require the supplier to provide P50/P95 curves of sync jitter rather than single-point marketing values. Under the buy pillar, this directly relates to the delivery risk of "Procuring E2: Key Points for the Field…" for the EgoLive project.

(Deep Dive · 174-3) Regarding EgoLive and E2: in long-duration dexterous data collection, thermal drift and bandwidth contention amplify soft-alignment error; hardware triggering is preferable to pure software timestamping. Under the buy pillar, this directly relates to the delivery risk of "Procuring E2: fields for the EgoLive project...".

(Deep Dive · 174-4) Regarding EgoLive and E2: failed samples must include a timeline health score, otherwise VLA will treat interpolated frames after repair as real contact. Under the buy pillar, this directly relates to the delivery risk of "Procuring E2: Key Points for the Field…" for the EgoLive project.

(Deep Dive · 174-5) Regarding EgoLive and E2: cross-day collection requires declaring the time-source switching strategy: whether CDC-ACM, PPS, or GNSS are mixed. Under the buy pillar, this directly relates to the delivery risk of "Procuring E2: Key Points for the Field…" for the EgoLive project.

(Deep dive · 174-6) Regarding EgoLive and E2: when the extrinsic versions of the wrist-mounted and head-mounted cameras are inconsistent, MANO supervision will be systematically biased; changing the wearer requires regression testing. Under the buy pillar, this is directly related to the delivery risk of the 'Procure E2: EgoLive project's fields…' item.

(Deep dive·174-7) Regarding EgoLive and E2: only when the OpenXR gesture stream and video frames share the same domain can semantic gestures be used as weak supervision rather than independent labels. Under the buy pillar, this directly relates to the delivery risk of "procuring E2: EgoLive project's fields…".

(Deep Dive · 174-8) Regarding EgoLive and E2: the DatasetServer segmentation limit and disk flush strategy affect whether the "last frame" is lost. Under the buy pillar, this directly relates to the delivery risk of "Procuring E2: Key Points for the Field…" for the EgoLive project.

(Extension · 174-B1) 2026-09-13 retrospective: matrix-based collection in the lab should define three-level primary keys—operator_id, session_id, and shard_id—to avoid filename collisions. If your team tags=E2,EgoLive,field gap self-check,procurement, it is recommended to add this to the project risk register.

(Extension · 174-B2) 2026-09-13 retrospective: when comparing against public benchmarks, only borrow task definitions and metrics, not data licensing boundaries. If your team tags=E2,EgoLive,field gap self-check,procurement, it is recommended to add this to the project risk register.

(Extension · 174-B3) 2026-09-13 retrospective: for ego-to-robot transfer, a separate coordinate-system appendix should be created covering the transformation chain of head, wrist, world, and robot_base. If your team tags=E2,EgoLive,field gap self-check,procurement, it is recommended to add this to the project risk register.

(Extension · 174-B4) 2026-09-13 retrospective: if HEVC transcoding re-stamps timestamps, the original_pts field must be preserved in the metadata. If your team tags=E2,EgoLive,field gap self-check,procurement, it is recommended to add this to the project risk register.

(Extension·174-B5) 2026-09-13 retrospective: ring-based supplementary points are suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. If your team's tags=E2, EgoLive, field gap self-check, procurement, it is recommended to write this into the project risk register.

Frequently Asked Questions (FAQ)

Q: Does TOBI provide the EgoLive dataset? Not provided. EgoLive is a public research/community resource; TOBI only discusses specification comparisons 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-stream.webp represent? Animated schematic showing E2 real-device recording and wearing form, not official EgoLive release content.

Q: What attachments should I prepare when requesting a quote? It is recommended to attach https://arxiv.org/abs/2604.23570, 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 E2 scenarios against EgoLive (field-gap self-check, procurement), please contact TOBI with the Must-field checklist to request 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-174-buy-e2-b102 · 1) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 2) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 3) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 4) A VLA recipe should declare the language instruction alignment method: manual trigger vs. ASR timestamps. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 5) Human-to-robot transfer requires declaring the action space: joint vs. end-effector vs. bimanual. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 6) It is recommended that procurement contract attachments include links to public papers for task reference only, without implying data transfer. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 7) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 8) During procurement review, require the supplier to provide P50/P95 curves of sync jitter, not single-point marketing figures. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 9) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 10) Failed samples must include a timeline health score; otherwise, VLA will treat interpolated frames after repair as real contact. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 11) Cross-day capture requires declaring the time source switching strategy: whether CDC-ACM, PPS, or GNSS are mixed. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 12) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 13) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 14) DatasetServer shard limits and disk flush strategy affect whether the "last frame" is lost. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 15) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 16) When comparing against public benchmarks, only borrow the task definitions and metrics, not the data licensing boundaries. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 17) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 18) If HEVC transcoding rewrites timestamps, the original_pts field must be preserved in the metadata. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 19) Ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 20) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 21) Collaborative Ego scenarios must declare the speech/instruction synchronization strategy to avoid audio-visual causal misalignment. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 22) QA spot checks should re-run the same script on a Linux host to ensure the delivery is auditable. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 23) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 24) When 60fps stereo capture is combined with a 30fps auxiliary stream, clearly specify the downsampling and phase rules. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 25) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 26) ORB-SLAM3-class VIO baselines emphasize multi-sensor timestamps; Ego devices should align to equivalent semantics. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 27) Open X-Embodiment emphasizes cross-platform action distributions; the Ego field schema should reserve an embodiment_id field. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 28) DROID-class robot data lacks human priors; E2's lightweight Ego is suitable as a pre-stage for human demonstration. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 29) The HaMeR lineage is sensitive to occlusion; ring + multi-path redundancy reduces the proportion of invisible frames. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 30) ActiveUMI demonstrates active perception; dual-channel acceptance of wrist-mounted plus head-mounted streams is the procurement-grade answer. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 31) World model training relies more on long-duration consistent timelines; random cropping of short clips destroys state continuity. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 32) Diffusion policies are sensitive to contact phase; the data card should annotate the start and end frames of contact_phase. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 33) The Sim2Real pipeline should not use different timestamp units in sim and real. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 34) Enterprise content funnel: paper page → spec page → prototype → small-batch data → scaled procurement, with exit criteria at each step. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 35) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 36) When linking to SDK documentation, fix the anchor to #device-sdk to reduce reader disorientation. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 37) The video poster matches the hero image, reducing first-screen CLS and trust cost. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 38) The FAQ must reiterate dataset boundaries to prevent sales from over-promising. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 39) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 40) Motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 41) Global shutter reduces geometric distortion in fast lateral motion scenarios compared to rolling shutter, benefiting stereo matching. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 42) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 43) fMP4 segments facilitate browser preview, but the training side requires a raw or lossless backup strategy. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 44) MCAP is well-suited to the ROS2 ecosystem; field naming should follow the team's schema registry. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 45) Scripts like linux_run_time_sync.sh should be versioned and cross-referenced with the firmware README. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 46) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 47) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 48) Health monitoring should include camera dropout, IMU saturation, remaining storage, and thermal throttling. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 49) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 50) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 51) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 52) A VLA recipe should declare the language instruction alignment method: manual trigger vs. ASR timestamps. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 53) Human-to-robot transfer requires declaring the action space: joint vs. end-effector vs. bimanual. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 54) It is recommended that procurement contract attachments include links to public papers for task reference only, without implying data transfer. When assessing E2 against EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-174-buy-e2-b102 · 55) 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 EgoLive (2026), archive this together with the acceptance checklist dated 2026-09-13.