gps-denied-onboard/_docs/00_research/01_source_registry/00_summary.md

Source Registry — Summary & Index

Mode A Phase 2 — engine Step 2 (Source Tiering & Exhaustive Web Investigation). Critical-novelty sensitivity per Step 0.5 in ../00_question_decomposition.md. Time windows applied:

• Lead-candidate / SOTA claims: prefer sources within last 6 months; up to 18 months if older is the official authority.
• Library/SDK API behaviour: must reflect the currently shipped version at search time (context7 mandatory per lead candidate).
• Established baselines (KLT, RANSAC, EKF, ORB, SIFT, GTSAM): no time window.

Investigation order saved in ../00_question_decomposition.md → "Next Step": SQ6 → SQ1 → SQ2 → SQ3+SQ4 per component (C1→C8) ✓ → C10 next → SQ5 interleaved → SQ8 → SQ9 synthesis at engine Step 8. SQ7 (datasets / SITL / replay) deferred to Test Spec (greenfield Step 5) per 2026-05-08 C9 / SQ7 restructure — see ../00_question_decomposition.md → "C9 / SQ7 Restructure" section.

This folder replaces the previous monolithic 01_source_registry.md. The full per-source description for any source #N in the table below lives in the category file linked in its row.

Category Index

Category	File	Sources	Status
SQ6 — ArduPilot Plane vs iNav external positioning	SQ6_external_positioning.md	#1–#24	Saturated for protocol-level architectural decision
SQ1 — Existing GPS-denied UAV systems	SQ1_existing_systems.md	#25–#37	Saturated
SQ2 — Canonical pipeline decomposition	SQ2_canonical_pipeline.md	#38–#42	Saturated
C1 — VIO candidates	C1_vio.md	#43–#56	Closed at documentary level
C2 — VPR candidates	C2_vpr.md	#57–#68	Mandatory pre-screen complete (5/5)
C3 — Matcher candidates	C3_matchers.md	#69–#81	Closed at documentary level
C4 — Pose estimation candidates	C4_pose_estimation.md	#82–#87	Closed at 3/N
C5 — State estimator / sensor fusion candidates	C5_state_estimator.md	#88–#91	Closed at 2/N (batch 1 closed)
C6 — Tile cache + spatial index candidates	C6_tile_cache_spatial_index.md	#92–#98	Closed at 2/N (batch 1 closed) — Cand 1 (mirror-suite-pattern) RECOMMENDED PRIMARY; Cand 2 (PostGIS+pgvector) DEFERRED secondary
C7 — On-Jetson inference runtime candidates	C7_inference_runtime.md	#99–#105	Closed at 3/N (batch 1 closed 2026-05-08) — Cand 1 (TensorRT native) RECOMMENDED PRIMARY; Cand 2 (ONNX Runtime + TRT EP) modern-competitive-lead-cross-architecture-portability; Cand 3 (pure PyTorch FP16) mandatory simple-baseline
C8 — MAVLink / MSP2 FC adapter candidates	C8_fc_adapter.md	#106–#113	Closed at 3/N (batch 1 closed 2026-05-08) — Cand 1 (pymavlink → MAVLink GPS_INPUT) RECOMMENDED PRIMARY for ArduPilot Plane; Cand 2 (MSP2_SENSOR_GPS via Python MSP V2) RECOMMENDED PRIMARY for iNav (locked SQ6 + AC-4.3 transport); Cand 3 (UBX impersonation via pyubx2 NAV-PVT) DEFERRED secondary for iNav after comparative-improvement verdict
C10 — Pre-flight cache provisioning (CROSS-COUPLING MINIMAL scope per 2026-05-08 user choice C; D-C6-3 + D-C7-7 confirmation pipelines only, operator tooling deferred to Plan-phase)	C10_preflight_provisioning.md	#114–#121	Closed at 2/N (batch 1 closed 2026-05-08) — D-C6-3 confirmation: direct faiss.write_index/faiss.read_index Python API + python-atomicwrites + content-hash verification gate at takeoff (FAISS MIT, atomicwrites MIT); D-C7-7 confirmation: hybrid Polygraphy CLI primary + trtexec for cache-reuse fast rebuilds + direct IBuilderConfig Python API escape hatch (Polygraphy + TensorRT 10.x Apache-2.0 throughout)
Mode B addendum (2026-05-08) — solution_draft01 assessment	MODEB_addendum.md	#122–#131 (10 sources)	New sources gathered for Mode B findings F1–F20: VINS-Mono GPL-3.0 LICENCE confirmation (#122), MegaLoc + UltraVPR + AirZoo aerial-VPR successor candidates (#123, #124, #125), CVE-2026-1579 MAVLink no-default-auth + CVE-2025-53644 OpenCV crafted-JPEG (#126, #127), ArduPilot MAVLink2 message-signing + iNav signing-gap (#128, #129), ArduPilot MAV_CMD_SET_EKF_SOURCE_SET no-deployed-GCS-implementer re-verification (#130), XoFTR + 2026 SAR-optical 24-matcher benchmark (#131).

Investigation Status

Sub-question	Status	Notes
SQ6 — ArduPilot vs iNav external positioning	Saturated for protocol-level architectural decision (further detail deferred to SQ8 for spoofing-side fields and to design phase for SITL parameter tuning)	Major finding: iNav has no inbound external-positioning MAVLink handler; AC-4.3 wording must be revised. See ../02_fact_cards/SQ6_fc_external_positioning.md "SQ6 Conclusions".
SQ1 — Existing GPS-denied UAV systems	Saturated. 13 sources logged across academic / open-source / commercial / defense-program / Ukraine-practitioner. Closest peer system: Twist Robotics OSCAR (deployed in Ukraine). Closest open-source pipeline-match: snktshrma/ngps_flight (NGPS, ArduPilot GSoC 2024 — LightGlue+SuperPoint+UKF+VISION_POSITION_ESTIMATE). Closest deployed commercial: Auterion Artemis (Skynode N + Visual Navigation, Ukraine-tested, 1000-mile range).	See ../02_fact_cards/SQ1_existing_systems.md cluster + working summary.
SQ2 — Canonical pipeline decomposition	Saturated. 5 surveys/benchmarks logged (Skoltech aerial VPR, U.Maine cross-view, OrthoLoC 2.5D geodata, AnyVisLoc low-altitude multi-view, NUDT 2026 sciopen survey). All converge on retrieval → matching → pose-estimation hierarchical framework with VIO/IMU as auxiliary. Two new architectural facts added to C1–C10: (a) AdHoP-style perspective-refinement loop between matching and PnP (+63% translation accuracy, method-agnostic), (b) DSM 2.5D dependency for full 6-DoF on aerial-to-satellite (must be resolved with the Suite Sat Service or accepted as a 3-DoF degraded mode). Practitioner runtime evidence: AnyLoc on RTX 3090 = 0.63s/descriptor, SuperGlue re-rank = 17–25s; on Jetson Orin Nano these are non-viable for our 400 ms p95 budget — must restrict to lightweight VPR (e.g., MixVPR / SALAD class) + LightGlue/XFeat-class matchers. See ../02_fact_cards/SQ2_canonical_pipeline.md "SQ2 Conclusions".
SQ3+SQ4 — Per-component candidates (C1–C10)	In progress — C1 (VIO) CLOSED at documentary level (Sources #43–#56). C2 (VPR) — mandatory pre-screen COMPLETE at documentary level (5 of 5 candidates): MixVPR (Sources #57+#58), SALAD (Sources #59+#60+#61), SelaVPR (Sources #62+#63), NetVLAD (Sources #64+#65+#66), EigenPlaces (Sources #67+#68 — closure 2026-05-08). All five mandatory candidates have per-mode API capability verification ✅, per-numbered-Restriction × per-numbered-AC sub-matrix written, and ../06_component_fit_matrix/C2_vpr.md rows populated. Conditional pre-screen candidates (AnyLoc / BoQ / DINOv2-VLAD) are GATED on a prerequisite INT8 quantization survey before they can be added to per-mode rows (per Fact #26 pre-screen rule). C3 closed at documentary level (Sources #69–#81). C4 closed at 3/N (Sources #82–#87). C5 CLOSED at 2/N — batch 1 closed 2026-05-08 (mandatory simple-baseline = Manual ESKF Solà 2017 [Sources #88–#89]; modern-competitive-lead-factor-graph = GTSAM iSAM2 + ImuFactor + smart factors + Marginals [Sources #90–#91]). C6 CLOSED at 2/N — batch 1 closed 2026-05-08 (Cand 1 RECOMMENDED PRIMARY = mirror-of-suite-satellite-provider pattern: PostgreSQL btree + bytea + FAISS HNSW + filesystem [Sources #92+#96+#97+#98]; Cand 2 DEFERRED secondary = PostGIS GiST + pgvector HNSW + filesystem [Sources #94+#95]; Source #93 = PostgreSQL btree multicolumn-indexes docs cross-cite). C7 CLOSED at 3/N — batch 1 closed 2026-05-08 (Cand 1 RECOMMENDED PRIMARY = TensorRT native [Sources #99+#104+#105]; Cand 2 modern-competitive-lead-cross-architecture-portability = ONNX Runtime + TRT EP [Source #100 + #103]; Cand 3 mandatory simple-baseline = pure PyTorch FP16 [Source #101]; Source #102 = YOLO26 Jetson Orin Nano Super benchmark; Source #103 = LightGlue+TRT+FP8 quantization-sensitivity finding driving D-C7-6 cross-component precision policy). C8 CLOSED at 3/N — batch 1 closed 2026-05-08 (Cand 1 RECOMMENDED PRIMARY for ArduPilot = pymavlink → MAVLink GPS_INPUT msg 232 cooperative-path [Sources #106+#107 + cross-cite SQ6 Source #4 AP_GPS_MAV.cpp ingestion-path]; Cand 2 RECOMMENDED PRIMARY for iNav = MSP2_SENSOR_GPS id 7939 / 0x1F03 via Python MSP V2 implementation [Sources #111+#112+#113 + cross-cite SQ6 Source #12+#13]; Cand 3 DEFERRED secondary for iNav = UBX impersonation via pyubx2 NAV-PVT [Sources #108+#109+#110 + cross-cite SQ6 Fact #10] with comparative-improvement verdict that does NOT clear user's "significant-improvement-only" bar over Cand 2; mid-batch correction via c8_inav_recovery=B preserved locked SQ6 + AC-4.3 + restrictions.md verdicts). C9 DROPPED from research scope per 2026-05-08 SQ7/C9 restructure (datasets/SITL/replay deferred to Test Spec greenfield Step 5). C10 CLOSED at 2/N — batch 1 closed 2026-05-08 under CROSS-COUPLING MINIMAL scope per 2026-05-08 user choice C (operator CLI/desktop tooling, sector classification, freshness pipeline deferred to Plan-phase): D-C6-3 confirmation = direct faiss.write_index/faiss.read_index Python API + python-atomicwrites + content-hash (SHA-256) verification gate at takeoff load + IO_FLAG_MMAP_IFC mmap [Sources #114+#115+#116]; D-C7-7 confirmation = hybrid Polygraphy CLI primary for INT8-calibrating builds + trtexec for cache-reuse fast rebuilds + direct IBuilderConfig Python API escape hatch [Sources #117+#118+#119+#120+#121]; no further C10 batches required at the research layer — operator tooling design enters at Plan-phase.	See ../02_fact_cards/C1_vio.md + ../02_fact_cards/C2_vpr.md + ../02_fact_cards/C3_matchers.md + ../02_fact_cards/C4_pose_estimation.md + ../02_fact_cards/C5_state_estimator.md + ../02_fact_cards/C6_tile_cache_spatial_index.md + ../02_fact_cards/C7_inference_runtime.md clusters; ../06_component_fit_matrix/C{1..7}_*.md rows.
SQ5 — Failure modes / deployment lessons	Not started (interleaved with SQ3/SQ4)
SQ7 — Datasets, SITL, replay environments	Deferred to Test Spec (greenfield Step 5) per 2026-05-08 C9 / SQ7 restructure	Fixture-class / test-infra-class — not researched in this Mode A run. Carryforward payload preserved in ../00_question_decomposition.md → "C9 / SQ7 Restructure" section.
SQ8 — Safety considerations (AC-NEW-4 / AC-NEW-7)	Not started	Carries the AP_GPS spoofing-signal probe deferred from SQ6.
SQ9 — End-to-end synthesis	Step 8 of engine (deferred)

---

Source Summary Table

Compact one-line index across all 121 sources. For full per-source description, follow the File link.

#	Title	Tier	File
1	Non-GPS Navigation — Plane documentation	L1	SQ6
2	GPS / Non-GPS Transitions — Plane documentation	L1	SQ6
3	EKF Source Selection and Switching — Plane documentation	L1	SQ6
4	ArduPilot AP_GPS_MAV.cpp (master)	L1	SQ6
5	ArduPilot PR #28750 — AP_NavEKF3 EK3_OPTION bits (GPS-denied testing)	L2	SQ6
6	ArduPilot Issue #15859 — EKF3 source switching (GPS↔NonGPS)	L4	SQ6
7	ArduPilot Issue #27193 — EK3 Source Switching wrong frame for GUIDED	L4	SQ6
8	ArduPilot Issue #23485 — fuse only External Nav Velocities	L4	SQ6
9	iNavFlight/inav telemetry/mavlink.c (master inbound switch)	L1	SQ6
10	iNav Wiki — MAVLink (frogmane edited 2025-12-11)	L1	SQ6
11	iNav Wiki — GPS and Compass setup	L1	SQ6
12	iNavFlight/inav docs/development/msp/README.md (MSP message reference)	L1	SQ6
13	iNavFlight/inav src/main/io/gps.c + target/common.h (master)	L1	SQ6
14	iNav Issue #10141 — dual GPS support	L4	SQ6
15	iNav docs/GPS_fix_estimation.md (master)	L1	SQ6
16	iNav docs/Settings.md (master)	L1	SQ6
17	iNav Issue #10588 — DeadReckoning weird behaviour during GPS outage	L4	SQ6
18	iNav Release 8.0.0 (highlights, Dec 2024)	L1	SQ6
19	iNav Release 9.0.0 / 9.0.1 + Release Notes wiki	L1	SQ6
20	MAVLink common message set — GPS_RAW_INT (24)	L1	SQ6
21	MAVLink PR #2110 — gps: add status and integrity information	L2	SQ6
22	AirDroper — GNSS Spoofing Filter companion device	L3	SQ6
23	ArduPilot PR #24135 — EKF3 robust to bad IMU and lane-switching	L2	SQ6
24	ArduPilot AP_NavEKF3 — VehicleStatus.cpp + AP_NavEKF3.cpp (master)	L1	SQ6
25	Twist Robotics OSCAR — visual navigation system (Ukraine deployment)	L2	SQ1
26	Ukraine Drones with Vision-Based Navigation Past Heavy Jamming (TWZ)	L2	SQ1
27	Ukraine's Ruta Missile Drone EW-Immune Navigation (Defense Express)	L2	SQ1
28	Kilometer-Scale GNSS-Denied UAV Navigation via Heightmap Gradients	L1	SQ1
29	Hierarchical Image Matching for UAV Absolute Visual Localization	L1	SQ1
30	Raptor — GPS-Denied UAV Navigation & Coordinate Extraction (Vantor)	L2	SQ1
31	Auterion Artemis program — long-range deep-strike completion	L1	SQ1
32	Auterion Skynode N — AI/CV for small autonomous systems	L2	SQ1
33	snktshrma/ngps_flight — NGPS for ArduPilot (GSoC 2024)	L1	SQ1
34	AerialExtreMatch — benchmark for extreme-view image matching/localization	L1	SQ1
35	DARPA Fast Lightweight Autonomy (FLA) program page + T&E review	L1	SQ1
36	DSMAC / TERCOM lineage — DTIC ADA315439	L1	SQ1
37	Electronic Warfare in Ukraine — Ukraine War Analytics	L3	SQ1
38	VPR for Aerial Imagery: A Survey (Skoltech, Moskalenko et al.)	L1	SQ2
39	Cross-View Geo-Localization: A Survey (U. Maine)	L1	SQ2
40	OrthoLoC: UAV 6-DoF Localization with Orthographic Geodata	L1	SQ2
41	AnyVisLoc — UAV visual localization, low-altitude multi-view	L1	SQ2
42	NUDT 2026 — survey on absolute visual localization for low-altitude UAV	L1	SQ2
43	VINS-Mono — robust monocular visual-inertial state estimator	L1	C1
44	VINS-Fusion — optimization-based multi-sensor state estimator	L1	C1
45	OpenVINS — open-source VI navigation research platform	L1	C1
46	Run VIO on NVIDIA Jetson — KAIST benchmark	L1	C1
47	OKVIS2 — realtime scalable VI-SLAM with loop closure	L1	C1
48	OKVIS2-X — open keyframe VI-SLAM with dense depth	L1	C1
49	Kimera-VIO — VIO with SLAM + 3D mesh (MIT-SPARK, BSD)	L1	C1
50	DROID-SLAM — deep visual SLAM (princeton-vl)	L1	C1
51	DPVO / DPV-SLAM — deep patch visual odometry	L1	C1
52	DPVO-QAT++ — heterogeneous QAT + CUDA kernel fusion for DPVO	L2	C1
53	Pure-VO baseline — KLT optical flow + 5-point/homography RANSAC (OpenCV)	L1	C1
54	OpenVINS — context7 per-mode capability lookup (/rpng/open_vins)	L1	C1
55	VINS-Mono README + VINS-Fusion context7 per-mode lookup	L1	C1
56	OKVIS2 — official README (smartroboticslab/okvis2, main)	L1	C1
57	OpenVPRLab — open-source VPR framework (MixVPR / BoQ / NetVLAD / GeM)	L1	C2
58	MixVPR canonical paper (WACV 2023, arXiv:2303.02190)	L1	C2
59	SALAD canonical implementation (serizba/salad, GPL-3.0)	L1	C2
60	SALAD canonical paper — Optimal Transport Aggregation (CVPR 2024)	L1	C2
61	OpenVPRLab DinoV2 backbone — context7 cross-source for ViT-B/14	L1	C2
62	SelaVPR canonical implementation (Lu-Feng/SelaVPR, MIT)	L1	C2
63	SelaVPR canonical paper (ICLR 2024, arXiv:2402.14505)	L1	C2
64	NetVLAD canonical implementation Relja/netvlad v1.03 (MIT)	L1	C2
65	NetVLAD modern PyTorch reproduction Nanne/pytorch-NetVlad	L2	C2
66	NetVLAD canonical paper (CVPR 2016 / TPAMI 2018, arXiv:1511.07247)	L1	C2
67	EigenPlaces canonical implementation (gmberton/EigenPlaces, MIT)	L1	C2
68	EigenPlaces canonical paper (ICCV 2023, arXiv:2308.10832)	L1	C2
69	LightGlue — context7 per-mode capability lookup (/cvg/lightglue)	L1	C3
70	LightGlue canonical implementation (cvg/LightGlue)	L1	C3
71	LightGlue canonical paper (ICCV 2023, arXiv:2306.13643)	L1	C3
72	LightGlue HuggingFace Transformers integration	L1	C3
73	LightGlue-ONNX — fabio-sim/LightGlue-ONNX (Jetson TensorRT path)	L2	C3
74	ALIKED canonical implementation (Shiaoming/ALIKED)	L1	C3
75	ALIKED canonical paper (TIM 2023, arXiv:2304.03608)	L1	C3
76	DISK canonical implementation (cvlab-epfl/disk, Apache-2.0)	L1	C3
77	DISK canonical paper — RL-trained local features (NeurIPS 2020)	L1	C3
78	SuperGlue canonical implementation (magicleap/SuperGluePretrainedNetwork)	L1	C3
79	SuperGlue canonical paper — graph-NN feature matching (CVPR 2020)	L1	C3
80	XFeat canonical implementation (verlab/accelerated_features, Apache-2.0)	L1	C3
81	XFeat canonical paper — accelerated features (CVPR 2024)	L1	C3
82	OpenCV canonical implementation — opencv/opencv (calib3d module)	L1	C4
83	OpenCV 4.x calib3d module canonical documentation	L1	C4
84	OpenGV canonical implementation (laurentkneip/opengv)	L1	C4
85	OpenGV canonical Doxygen documentation portal	L1	C4
86	GTSAM canonical implementation (borglab/gtsam, BSD-3)	L1	C4
87	GTSAM canonical Python documentation via context7	L1	C4
88	Solà 2017 — "Quaternion kinematics for the error-state Kalman filter" (arXiv:1711.02508)	L1	C5
89	Reference open-source ESKF implementations (canonical-paper-derived)	L2	C5
90	GTSAM ImuFactor / CombinedImuFactor / PreintegratedImuMeasurements / PreintegratedCombinedMeasurements (context7 indexed)	L1	C5
91	GTSAM ISAM2 / IncrementalFixedLagSmoother / Marginals with iSAM2 results (context7 indexed)	L1	C5
92	Parent-suite satellite-provider existing pattern (PostgreSQL + Dapper + filesystem tile storage; verified directly)	L1	C6
93	PostgreSQL 16 official documentation — Multicolumn Indexes + btree access method	L1	C6
94	PostGIS official documentation — GiST + KNN distance ordering + ST_DWithin	L1	C6
95	pgvector official documentation — HNSW index API (context7 + canonical README)	L1	C6
96	FAISS official documentation — IndexFlatL2 / IndexHNSWFlat / IndexIVFFlat (context7 indexed)	L1	C6
97	Postgres on NVIDIA Jetson Orin Nano — March 2026 Medium article + Coding Steve minimal-config guide	L2	C6
98	Slippy Map Tilenames — OpenStreetMap canonical specification (Web Mercator XYZ)	L1	C6
99	NVIDIA TensorRT 10.x official documentation portal (context7-indexed /nvidia/tensorrt)	L1	C7
100	Microsoft ONNX Runtime official documentation (context7-indexed /microsoft/onnxruntime) + Jetson AI Lab community wheel index	L1	C7
101	PyTorch official documentation (context7-indexed /pytorch/pytorch) + Jetson AI Lab PyTorch wheel availability for JetPack 6	L1	C7
102	Ultralytics YOLO26 benchmark suite on Jetson Orin Nano Super (April 2026)	L2	C7
103	LightGlue ONNX Runtime + TensorRT acceleration + FP8 ModelOpt quantization findings (Fabio Sim's Journal)	L2	C7
104	JetPack SDK release notes (NVIDIA official) — JetPack 6.0 / 6.1 / 6.2 version matrix	L1	C7
105	TensorRT-on-Jetson canonical install constraints (Ultralytics issue reports + NVIDIA forum)	L2	C7
106	ArduPilot Pymavlink (context7-indexed /ardupilot/pymavlink) — canonical Python MAVLink stack	L1	C8
107	ArduPilot Plane Non-GPS Position Estimation + MAVProxy GPS Input module dev docs (GPS1_TYPE=14, EK3_SRC1_POSXY=3)	L1	C8
108	pyubx2 (context7-indexed /semuconsulting/pyubx2) — canonical Python UBX/NMEA/RTCM3 parser	L1	C8
109	u-blox NEO-M9N Integration Manual (UBX-19014286) + u-blox 8/M8 Receiver Description (UBX-13003221) — UBX-NAV-PVT canonical specification	L1	C8
110	iNav gps_ublox.c source (master) — UBX validation gates gpsMapFixType() requires flags & 0x01 = 1 AND fixType ∈ {2,3}	L1	C8
111	iNav docs/development/msp/README.md (master) — MSP2_SENSOR_GPS (7939 / 0x1F03) canonical 36-byte payload spec	L1	C8
112	Python MSP2 implementations: YAMSPy + INAV-Toolkit inav_msp.py (MSP V2 msp_v2_encode with CRC-8 DVB-S2)	L2	C8
113	iNav src/main/msp/msp_protocol_v2_sensor.h (master) — MSP V2 sensor command-ID range (0x1F00-0x1FFF)	L1	C8
114	FAISS write_index / read_index Python API + on-disk format + security warning (canonical wiki + context7)	L1	C10
115	FAISS IndexHNSWFlat per-vector memory + on-disk file size formula (Discussions #3953 + C++ API docs)	L2	C10
116	Python atomic file write pattern (gocept blog + python-atomicwrites docs + Python Issue 8604)	L2	C10
117	Polygraphy polygraphy convert CLI for TensorRT INT8 engine build with calibration cache reuse (NVIDIA TensorRT repo + context7)	L1	C10
118	Polygraphy Calibrator class API — algo defaults + dynamic-shapes calibration profile + warning behavior (NVIDIA TRT/Polygraphy SDK docs)	L1	C10
119	trtexec CLI for one-off engine builds — INT8/FP16 flags + calibration cache support (NVIDIA TRT SDK docs)	L1	C10
120	TensorRT INT8 calibration corpus size guidance (~500-1000 images) — Jetson AGX Orin (vendor engineering guide)	L2	C10
121	Direct TensorRT IBuilderConfig + IInt8EntropyCalibrator2 Python API (NVIDIA TRT Python API docs, cross-cite from C7 #105)	L1	C10