SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.06244 · 2020

CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 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/2006.06244.json · badge: /api/ran/2006.06244.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
clovaai/CLEval canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_area_precision Ran
ran, honoured the contract we drafted
clovaai/CLEval/cleval/eval_functions.py
code served (permissive licence) · get_code("dd4d62930069dfce")
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 tuple, ndim 3, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

class Box:
    """Stand-in Box class with area() method and & operator for intersection"""
    def __init__(self, x1, y1, x2, y2):
        self.x1 = x1
        self.y1 = y1
        self.x2 = x2
        self.y2 = y2
    
    def area(self):
        """Calculate box area"""
        width = max(0, self.x2 - self.x1)
        height = max(0, self.y2 - self.y1)
        return width * height
    
    def __and__(self, other):
        """Calculate intersection area with another box"""
        x1_inter = max(self.x1, other.x1)
        y1_inter = max(self.y1, other.y1)
        x2_inter = min(self.x2, other.x2)
        y2_inter = min(self.y2, other.y2)
        
        width = max(0, x2_inter - x1_inter)
        height = max(0, y2_inter - y1_inter)
        return width * height

# Create ground truth boxes
gt_boxes = [
    Box(0, 0, 10, 10),
    Box(20, 20, 30, 30),
]

# Create detection boxes
det_boxes = [
    Box(2, 2, 12, 12),
    Box(22, 22, 32, 32),
    Box(50, 50, 60, 60),
]

# Area precision constraint threshold
ap_constraint = 0.5

ARGS = {
    "gt_boxes": gt_boxes,
    "det_boxes": det_boxes,
    "ap_constraint": ap_constraint,
}
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 tuple, ndim 3, dtype family float — a tuple output has no array shape of its own; none is stated
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
prepare_gt Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
clovaai/CLEval/cleval/eval_functions.py
code served (permissive licence) · get_code("6a0756a0ab418996")
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 tuple. 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

torch.manual_seed(0)

class GTBox:
    """Stand-in class for ground truth boxes."""
    def __init__(self, transcription, is_dc=False, scale=None, vertices=None):
        self.transcription = transcription
        self.is_dc = is_dc
        self.scale = scale
        self.vertices = vertices if vertices is not None else np.array([[0, 0], [1, 0], [1, 1], [0, 1]])
    
    def pseudo_character_center(self, vertical_aspect_ratio_thresh):
        """Return a pseudo character center point."""
        return np.array([0.5, 0.5])
    
    def __and__(self, other):
        """Compute intersection area (stub implementation)."""
        return 0.1  # Non-zero to trigger the subtract operation
    
    def subtract(self, other):
        """Subtract another box from this one (no-op stub)."""
        pass

# Create sample ground truth boxes
gt_boxes = [
    GTBox(transcription="hello", is_dc=False, scale=1.0),
    GTBox(transcription="world", is_dc=False, scale=1.5),
    GTBox(transcription="ignore", is_dc=True, scale=2.0),
]

ARGS = {
    "gt_boxes": gt_boxes,
    "is_case_sensitive": False,
    "vertical_aspect_ratio_thresh": 1.5,
    "scale_range": (0.5, 2.5),
}
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 tuple — a tuple output has no array shape of its own; none is 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Despite the recent success of text detection and recognition methods, existing evaluation metrics fail to provide a fair and reliable comparison among those methods. In addition, there exists no end-to-end evaluation metric that takes characteristics of OCR tasks into account. Previous end-to-end metric contains cascaded errors from the binary scoring process applied in both detection and recognition tasks. Ignoring partially correct results raises a gap between quantitative and qualitative analysis, and prevents fine-grained assessment. Based on the fact that character is a key element of text, we hereby propose a Character-Level Evaluation metric (CLEval). In CLEval, the \textit{instance matching} process handles split and merge detection cases, and the \textit{scoring process} conducts character-level evaluation. By aggregating character-level scores, the CLEval metric provides a fine-grained evaluation of end-to-end results composed of the detection and recognition as well as individual evaluations for each module from the end-performance perspective. We believe that our metrics can play a key role in developing and analyzing state-of-the-art text detection and recognition methods. The evaluation code is publicly available at https://github.com/clovaai/CLEval.

For agents

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

get_harvested_code_for_paper("2006.06244")
get_code_for_paper("2006.06244")
have("2006.06244")

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

curl https://syntology.ai/api/ran/2006.06244.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.06244.svg)](https://syntology.ai/paper/2006.06244)

Connect an agent — have() is free.