SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.04522 · 2026

ANN Search: Recall What Matters

Dimitris Dimitropoulos, Nikos Mamoulis

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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 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/2606.04522.json · badge: /api/ran/2606.04522.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
gouyt13/SymphonyQG community
Papers with Code archive
1 ran · 0 no recorded run
facebookresearch/faiss community
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
calc_ratio Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
gouyt13/SymphonyQG/reproduce/utils/avg_distance_ratio.py
code served (permissive licence) · get_code("0d093d8fa0702296")
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) and returned float, ndim 0, dtype family float, shape () 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 torch
import numpy as np

torch.manual_seed(0)

# The function takes two parameters: distances and gt_distances
# Both are used with sorted() and zip(), so they should be iterables of numeric values
# The function compares d2 < 0.0001 and computes d1 / d2, so they should be floats

distances = [0.5, 0.3, 0.8, 0.2]
gt_distances = [0.4, 0.25, 0.9, 0.15]

ARGS = {
    "distances": distances,
    "gt_distances": gt_distances,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
counts_to_PR Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/faiss/contrib/evaluation.py
code served (permissive licence) · get_code("6a202b9b805f99a8")
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) and returned tuple, ndim 1, 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

# Test case 1: overall mode
ngt_overall = np.array([5, 3, 7])
nres_overall = np.array([4, 2, 6])
ninter_overall = np.array([3, 2, 5])

# Test case 2: average mode
ngt_average = np.array([5, 0, 7, 3])
nres_average = np.array([4, 0, 6, 2])
ninter_average = np.array([3, 0, 5, 1])

ARGS = {
    'ngt': ngt_overall,
    'nres': nres_overall,
    'ninter': ninter_overall,
    'mode': 'overall'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 1, 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

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

Approximate Nearest Neighbor (ANN) search has become a core primitive in information retrieval and modern machine learning tasks, from classification to retrieval-augmented generation. The community evaluates and tunes ANN algorithms primarily on their throughput at a given Recall@k, the fraction of true exact neighbors retrieved. We argue that what really matters in ANN search is the quality of the retrieved results and not their overlap with the true kNN set. We show that using Recall@k to assess retrieval quality forces unnecessary computational overhead and investigate replacing it by 1/Ratio@k, the inverse approximation ratio. 1/Ratio@k evaluates the differences between the distances of the retrieved and true neighbors. It is judge-free, hyperparameter-free, and computable from standard ANN benchmark inputs alone. We benchmark state-of-the-art ANN algorithms across diverse datasets spanning a wide range of intrinsic dimensionalities, evaluating the two metrics comprehensively across efficiency, downstream classification, and retrieval-augmented generation. On the efficiency axis, optimizing for 1/Ratio@k reaches operational quality thresholds at a substantially lower computational cost than Recall@k. In downstream tasks, performance indicators (label precision, semantic similarity, BERTScore, and LLM-graded quality) remain highly stable even when Recall@k drops significantly. The inverse approximation ratio, on the other hand, closely mirrors this stability, tracking true utility much better than Recall@k. Ultimately, while Recall@k overstates the true cost of approximation, 1/Ratio@k offers a more accurate, deployable proxy for actual ANN quality.

For agents

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

get_harvested_code_for_paper("2606.04522")
get_code_for_paper("2606.04522")
have("2606.04522")

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

curl https://syntology.ai/api/ran/2606.04522.json

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

[![Syntology run record](https://syntology.ai/api/ran/2606.04522.svg)](https://syntology.ai/paper/2606.04522)

Connect an agent — have() is free.