lingbot-map
(ECCV 2026 oral & best paper candidate) LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Could not verifysource: GitHubPythonApache-2.0commit 849e690bb086
Python, Apache-2.0 licensed.
Argusic could not get lingbot-map running. An Argusic agent installed it in 3.2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Installs in a venv with CPU PyTorch; core model forward pass and streaming inference run end-to-end on CPU with synthetic data, producing predicted camera poses and depth maps; CUDA-dependent scripts and pre-trained-weight loading are not exercised.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 50 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- min(scale_frames, S_true) in lingbot_map/aggregator/stream.py lines 340/353 raises RuntimeError when S_true/S_global is a tensor with >1 element0.5 minutes
- Install time
- 3 minutes
- Cold machine to finish
- 9 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- pip install -e . succeeded; python3 -c 'from lingbot_map.models.gct_stream import GCTStream; m=GCTStream(); m.forward(torch.randn(1,1,3,112,112), num_frame_for_scale=8, num_frame_per_block=1, causal_inference=True)' returned dict with pose_enc[1,1,9], depth[1,1,112,112,1], depth_conf[1,1,112,112]; m.inference_streaming(torch.randn(10,3,112,112), num_scale_frames=8) returned pose_enc[1,10,9], depth[1,10,112,112,1]
- Model tokens used
- 211,756
- Exact commit tested
- 849e690bb086
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Install**: Created a venv, installed PyTorch 2.6.0 (CPU), all deps, and `pip install -e .` succee… **Key bug found and fixed**: `lingbot_map/aggregator/stream.py` line 340 and 353 called `min(scale_… **Verification**: The core model builds (1,156,803,828 params), `.forward()` with a single 112×112 … **Can't run without CUDA**: `gct_profile.py`, `scripts/benchmark_gct_memory.py`, and `benchmark/` e… tokens used 211,756 Now I have all the data. Let me produce the final report. Here's my comprehensive assessment: **Install**: Created a venv, installed PyTorch 2.6.0 (CPU), all deps, and `pip install -e .` succee… **Key bug found and fixed**: `lingbot_map/aggregator/stream.py` line 340 and 353 called `min(scale_… **Verification**: The core model builds (1,156,803,828 params), `.forward()` with a single 112×112 … **Can't run without CUDA**: `gct_profile.py`, `scripts/benchmark_gct_memory.py`, and `benchmark/` e…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 3.2 minutes, faster than the median of the 8 comparable projects Argusic has measured.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- An agent with no time limit did not get it running.
Of the 9 Python projects Argusic has installed and timed, lingbot-map was the 4th fastest to reach a running state, and 5 of 9 reached one at all.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Did not run | 20.00 | 0.09 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.05 |
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/lingbot-map)Questions
- Does lingbot-map run?
- Argusic could not verify that lingbot-map runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test lingbot-map?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 849e690bb086. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test lingbot-map?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does lingbot-map take to install?
- 3.2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does lingbot-map need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing lingbot-map?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does lingbot-map compare with the alternatives?
- Of the 9 Python projects Argusic has installed and timed, lingbot-map was the 4th fastest to reach a running state, and 5 of 9 reached one at all.
- Where is the evidence for lingbot-map?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.