SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.02840 · 2020

Assisted Perception: Optimizing Observations to Communicate State

arXiv · PDF · Open in the Atlas

Code that ran

4 of 7 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, 0 violated it and 2 have no contract verdict; 2 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; 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/2008.02840.json · badge: /api/ran/2008.02840.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
rddy/ASE community (classifier label)
classifier basis not recorded on the link
4 ran · 3 no recorded run
FunctionStatusWhere it lives
build_reward Ran
ran on a synthesized input
rddy/ASE/sensei/gw_viz.py
code served (permissive licence) · get_code("bf550853d4df4f1a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (6, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import enum

class Actions(enum.IntEnum):
    STAY = 0
    LEFT = 1
    UP = 2
    RIGHT = 3
    DOWN = 4

# Create a small state_action_reward array
# Shape: (xlen=2, ylen=3, na=5) where na is number of actions
xlen, ylen, na = 2, 3, 5
state_action_reward = np.random.randn(xlen, ylen, na).astype(np.float32)

# Introduce some NaNs to test the fill logic
state_action_reward[0, 0, 1] = np.nan
state_action_reward[1, 2, 3] = np.nan
state_action_reward[0, 1, 2] = np.nan

ARGS = {
    "state_action_reward": state_action_reward,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (6, 5) — shape (6, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_circle Ran
ran; our contract draft was wrong, not the code
rddy/ASE/deps/rendering.py
code served (permissive licence) · get_code("2c06fa905ea7fdda")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned FilledPolygon. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import math

# Mock OpenGL functions since they won't be available in sandbox
def glColor4f(*args):
    pass

def glLineWidth(width):
    pass

def glBegin(mode):
    pass

def glVertex3f(x, y, z):
    pass

def glEnd():
    pass

GL_QUADS = 0x0007
GL_POLYGON = 0x0009
GL_TRIANGLES = 0x0004
GL_LINE_LOOP = 0x0002
GL_LINE_STRIP = 0x0003

# Define the classes from the function
class Attr(object):
    def enable(self):
        raise NotImplementedError
    
    def disable(self):
        pass

class Color(Attr):
    def __init__(self, vec4):
        self.vec4 = vec4
    
    def enable(self):
        glColor4f(*self.vec4)

class LineWidth(Attr):
    def __init__(self, stroke):
        self.stroke = stroke
    
    def enable(self):
        glLineWidth(self.stroke)

class Geom(object):
    def __init__(self):
        self._color = Color((0, 0, 0, 1.0))
        self.attrs = [self._color]
    
    def render(self):
        for attr in reversed(self.attrs):
            attr.enable()
        self.render1()
        for attr in self.attrs:
            attr.disable()
    
    def render1(self):
        raise NotImplementedError
    
    def add_attr(self, attr):
        self.attrs.append(attr)
    
    def set_color(self, r, g, b):
        self._color.vec4 = (r, g, b, 1)

class FilledPolygon(Geom):
    def __init__(self, v):
        Geom.__init__(self)
        self.v = v
    
    def render1(self):
        if len(self.v) == 4:
            glBegin(GL_QUADS)
        elif len(self.v) > 4:
            glBegin(GL_POLYGON)
        else:
            glBegin(GL_TRIANGLES)
        for p in self.v:
            glVertex3f(p[0], p[1], 0)
        glEnd()

class PolyLine(Geom):
    def __init__(self, v, close):
        Geom.__init__(self)
        self.v = v
        self.close = close
        self.linewidth = LineWidth(1)
        self.add_attr(self.linewidth)
    
    def render1(self):
        glBegin(GL_LINE_LOOP if self.close else GL_LINE_STRIP)
        for p in self.v:
            glVertex3f(p[0], p[1], 0)
        glEnd()
    
    def set_linewidth(self, x):
        self.linewidth.stroke = x

def make_circle(radius=10, res=30, filled=True):
    points = []
    for i in range(res):
        ang = 2 * math.pi * i / res
        points.append((math.cos(ang) * radius, math.sin(ang) * radius))
    if filled:
        return FilledPolygon(points)
    else:
        return PolyLine(points, True)

ARGS = {
    "radius": 10,
    "res": 30,
    "filled": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FilledPolygon — a FilledPolygon output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a FilledPolygon output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_polygon Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rddy/ASE/deps/rendering.py
code served (permissive licence) · get_code("d11e06eecd6b20b0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned FilledPolygon. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Mock OpenGL functions since we're not rendering
def glColor4f(*args):
    pass

def glLineWidth(width):
    pass

def glBegin(mode):
    pass

def glVertex3f(x, y, z):
    pass

def glEnd():
    pass

GL_QUADS = 0x0007
GL_POLYGON = 0x0009
GL_TRIANGLES = 0x0004
GL_LINE_LOOP = 0x0002
GL_LINE_STRIP = 0x0003

# Define Attr base class
class Attr(object):
    def enable(self):
        raise NotImplementedError
    
    def disable(self):
        pass

# Define Color class
class Color(Attr):
    def __init__(self, vec4):
        self.vec4 = vec4
    
    def enable(self):
        glColor4f(*self.vec4)

# Define LineWidth class
class LineWidth(Attr):
    def __init__(self, stroke):
        self.stroke = stroke
    
    def enable(self):
        glLineWidth(self.stroke)

# Define Geom base class
class Geom(object):
    def __init__(self):
        self._color = Color((0, 0, 0, 1.0))
        self.attrs = [self._color]
    
    def render(self):
        for attr in reversed(self.attrs):
            attr.enable()
        self.render1()
        for attr in self.attrs:
            attr.disable()
    
    def render1(self):
        raise NotImplementedError
    
    def add_attr(self, attr):
        self.attrs.append(attr)
    
    def set_color(self, r, g, b):
        self._color.vec4 = (r, g, b, 1)

# Define FilledPolygon class
class FilledPolygon(Geom):
    def __init__(self, v):
        Geom.__init__(self)
        self.v = v
    
    def render1(self):
        if len(self.v) == 4:
            glBegin(GL_QUADS)
        elif len(self.v) > 4:
            glBegin(GL_POLYGON)
        else:
            glBegin(GL_TRIANGLES)
        for p in self.v:
            glVertex3f(p[0], p[1], 0)
        glEnd()

# Define PolyLine class
class PolyLine(Geom):
    def __init__(self, v, close):
        Geom.__init__(self)
        self.v = v
        self.close = close
        self.linewidth = LineWidth(1)
        self.add_attr(self.linewidth)
    
    def render1(self):
        glBegin(GL_LINE_LOOP if self.close else GL_LINE_STRIP)
        for p in self.v:
            glVertex3f(p[0], p[1], 0)
        glEnd()
    
    def set_linewidth(self, x):
        self.linewidth.stroke = x

# Define make_polygon function
def make_polygon(v, filled=True):
    if filled:
        return FilledPolygon(v)
    else:
        return PolyLine(v, True)

# Create test vertices - a list of tuples representing 2D points
vertices = [(0.0, 0.0), (1.0, 0.0), (1.0, 1.0), (0.0, 1.0)]

ARGS = {
    'v': vertices,
    'filled': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type FilledPolygon — a FilledPolygon output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a FilledPolygon output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
shape Ran
ran on a synthesized input
rddy/ASE/sensei/gw_viz.py
code served (permissive licence) · get_code("f35cb9713634b966")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family float, shape (2, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import enum

class Actions(enum.IntEnum):
    STAY = 0
    LEFT = 1
    UP = 2
    RIGHT = 3
    DOWN = 4

ACTION_DELTA = {Actions.STAY: (0, 0), Actions.LEFT: (-1, 0), Actions.UP: (0, 1), Actions.RIGHT: (1, 0), Actions.DOWN: (0, -1)}

def shape(state_reward: np.ndarray, state_potential: np.ndarray, discount: float=0.99) -> np.ndarray:
    """Shape `state_reward` with `state_potential`.

    Args:
        state_reward: a two-dimensional array, indexed by `(i,j)`.
        state_potential: a two-dimensional array of the same shape as `state_reward`.
        discount: discount rate of MDP.

    Returns:
        A state-action reward `sa_reward`. This is three-dimensional array,
        indexed by `(i,j,a)`, where `a` is an action indexing into `DIRECTIONS`.
        `sa_reward[i,j,a] = state_reward[i, j] + state_potential[i', j'] - state_potential[i,j]`,
        where `i', j'` is the successor state after taking action `a`.
    """
    assert state_reward.ndim == 2
    assert state_reward.shape == state_potential.shape
    padded_reward = np.pad(state_reward.astype(np.float32), pad_width=[(1, 1), (1, 1)], constant_values=np.nan)
    padded_potential = np.pad(state_potential.astype(np.float32), pad_width=[(1, 1), (1, 1)], constant_values=np.nan)
    res = []
    for x_delta, y_delta in ACTION_DELTA.values():
        axis = 0 if x_delta else 1
        delta = x_delta + y_delta
        new_potential = discount * np.roll(padded_potential, -delta, axis=axis)
        shaped = padded_reward + new_potential - padded_potential
        res.append(shaped[1:-1, 1:-1])
    return np.array(res).transpose((1, 2, 0))

# Create small 2D arrays for state_reward and state_potential
state_reward = np.array([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]], dtype=np.float32)
state_potential = np.array([[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]], dtype=np.float32)
discount = 0.99

ARGS = {
    "state_reward": state_reward,
    "state_potential": state_potential,
    "discount": discount,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family float, shape (2, 3, 5) — shape (2, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
build_transitions Not yet run
unverified (harvested, no recorded run)
rddy/ASE/sensei/gw_viz.py
code served (permissive licence) · get_code("6040cf7fff57d910")
How it ran

no invocation recorded.

evaluate_baseline_guides Not yet run
unverified (harvested, no recorded run)
rddy/ASE/sensei/ase.py
code served (permissive licence) · get_code("de52590f0c1a044d")
How it ran

no invocation recorded.

get_display Not yet run
unverified (harvested, no recorded run)
rddy/ASE/deps/rendering.py
pointer only (licence: MIT); the stored copy get_code serves, from semitable/multiagent-particle-envs, is pointer only (licence: MIT) · get_code("10da81242bba7f38")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from semitable/multiagent-particle-envs, and MIT, as GitHub detects it on that repository, is in the permissive set, but a licence decision keeps the body a pointer: its licence file names an outside party, so it may cover vendored code rather than the repository owner's files (recorded as pointer:licence_names_third_party_corporation). 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 4 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.

FunctionAlso present inEarliest-datedOthers named
make_circle 4 other papers
2 dated earlier, 2 later
1810.02912 (2018-10)
Actor-Attention-Critic for Multi-Agent Reinforcement Learning
2007.03102 (2020-07)
Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams
2011.00401 (2020-11)
The MAGICAL Benchmark for Robust Imitation
and 1 more not named here
get_display 3 other papers
2 dated earlier, 1 later
1810.02912 (2018-10)
Actor-Attention-Critic for Multi-Agent Reinforcement Learning
2006.07869 (2020-06)
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
2505.05262 (2025-05)
Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
make_polygon 3 other papers
2 dated earlier, 1 later
1810.02912 (2018-10)
Actor-Attention-Critic for Multi-Agent Reinforcement Learning
2007.03102 (2020-07)
Natural Emergence of Heterogeneous Strategies in Artificially Intelligent Competitive Teams
2505.05262 (2025-05)
Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration

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

We aim to help users estimate the state of the world in tasks like robotic teleoperation and navigation with visual impairments, where users may have systematic biases that lead to suboptimal behavior: they might struggle to process observations from multiple sensors simultaneously, receive delayed observations, or overestimate distances to obstacles. While we cannot directly change the user's internal beliefs or their internal state estimation process, our insight is that we can still assist them by modifying the user's observations. Instead of showing the user their true observations, we synthesize new observations that lead to more accurate internal state estimates when processed by the user. We refer to this method as assistive state estimation (ASE): an automated assistant uses the true observations to infer the state of the world, then generates a modified observation for the user to consume (e.g., through an augmented reality interface), and optimizes the modification to induce the user's new beliefs to match the assistant's current beliefs. We evaluate ASE in a user study with 12 participants who each perform four tasks: two tasks with known user biases -- bandwidth-limited image classification and a driving video game with observation delay -- and two with unknown biases that our method has to learn -- guided 2D navigation and a lunar lander teleoperation video game. A different assistance strategy emerges in each domain, such as quickly revealing informative pixels to speed up image classification, using a dynamics model to undo observation delay in driving, identifying nearby landmarks for navigation, and exaggerating a visual indicator of tilt in the lander game. The results show that ASE substantially improves the task performance of users with bandwidth constraints, observation delay, and other unknown biases.

For agents

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

get_harvested_code_for_paper("2008.02840")
get_code_for_paper("2008.02840")
have("2008.02840")

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

curl https://syntology.ai/api/ran/2008.02840.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.02840.svg)](https://syntology.ai/paper/2008.02840)

Connect an agent — have() is free.