SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.06729 · 2026

Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds

Yang Xu, Vaneet Aggarwal, Jiefu Zhang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 13 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 9 failures of our instrument; 3 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2603.06729.json · badge: /api/ran/2603.06729.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
jznmsl/PSS-Social canonical (classifier label)
classifier basis: census
10 ran · 3 no recorded run
FunctionStatusWhere it lives
count_parameters Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/ds_rnn.py
pointer only (licence: NONE) · get_code("a1705ef3e6f88aba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

detect_agent_type Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/eval_baselines.py
pointer only (licence: NONE) · get_code("44529b07c8dd5db0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_agent Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/eval_kcap_ablation.py
pointer only (licence: NONE) · get_code("c06c6db997b0f5b9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

find_dsrnn_seeds Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/eval_dsrnn.py
pointer only (licence: NONE) · get_code("fa5fff9ee520d222")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/run_social.py
pointer only (licence: NONE) · get_code("03c29f9a75f44531")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_optimal_settings Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/run_social.py
pointer only (licence: NONE) · get_code("cc3dcf26895f9aba")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_social_experiment_config Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/pss_social.py
pointer only (licence: NONE) · get_code("77e4c510ba7ba2f2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

parse_scenario_mix Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/train_baselines.py
pointer only (licence: NONE) · get_code("0bf4bbcad1f6e6cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

run_episode_with_recording Ran
ran; our contract draft was wrong, not the code
jznmsl/PSS-Social/visualize_social.py
pointer only (licence: NONE) · get_code("cd101e69ee385ff9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sanitize_array Ran
ran, violated the contract we drafted
jznmsl/PSS-Social/pss_social.py
pointer only (licence: NONE) · get_code("d03b451dd7fa91de")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

evaluate_recurrent_agent Not yet run
unverified (harvested, no recorded run)
jznmsl/PSS-Social/eval_kcap_ablation.py
pointer only (licence: NONE) · get_code("baa7ab9cda582619")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

evaluate_recurrent_agent Not yet run
unverified (harvested, no recorded run)
jznmsl/PSS-Social/eval_unified.py
pointer only (licence: NONE) · get_code("4eb92a665215b359")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

extract_positions Not yet run
unverified (harvested, no recorded run)
jznmsl/PSS-Social/visualize_social.py
pointer only (licence: NONE) · get_code("d37bed2d677b30ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, jznmsl/PSS-Social when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Navigating safely through dense crowds requires collision avoidance that generalizes beyond the densities seen during training. Learning-based crowd navigation can break under out-of-distribution crowd sizes due to density-sensitive observation normalization and social-cost scaling, while analytical solvers often remain safe but freeze in tight interactions. We propose a reinforcement learning approach for dense, variabledensity navigation that attains zero-shot density generalization using a density-invariant observation encoding with densityrandomized training and physics-informed proxemic reward shaping with density-adaptive scaling. The encoding represents the distance-sorted K nearest pedestrians plus bounded crowd summaries, keeping input statistics stable as crowd size grows. Trained with N ∈ [11,16] pedestrians in a 3m × 3m arena and evaluated up to N = 21 pedestrians (1.3× denser), our policy reaches the goal in > 99% of episodes and achieves 86% collision-free success in random crowds, with markedly less freezing than analytical methods and a > 60-point collisionfree margin over learning-based benchmark methods. Codes are available at https://github.com/jznmsl/PSS-Social.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2603.06729")
get_code_for_paper("2603.06729")
have("2603.06729")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2603.06729.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2603.06729.svg)](https://syntology.ai/paper/2603.06729)

Connect an agent — have() is free.