SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.14732 · ICML · 2024

Residual Quantization with Implicit Neural Codebooks

Jakob Verbeek, Matthijs Douze, Fair At Meta, Iris Huijben, Matthew Muckley, Ruud Van Sloun

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, 0 violated it and 3 have no contract verdict; 7 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/2401.14732.json · badge: /api/ran/2401.14732.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
facebookresearch/qinco marked official in Papers with Code
Papers with Code archive
10 ran · 3 no recorded run
FunctionStatusWhere it lives
IVFBook Ran
ran on a synthesized input
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("f409546bd6543923")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

QBlockFFN Ran
ran on a synthesized input
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("0154f6c6afc2cfeb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

QConcat Ran
ran on a synthesized input
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("205ed094438d5ff2")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

approx_compute_batch_distances Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("bc1a701de4211b3d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

approx_pairwise_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("e078bbf9885dd047")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

compute_batch_distances Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("066d4ad3460ffdf4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

exact_compute_batch_distances Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("ec62f37b60e7ab4c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

exact_pairwise_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("71c1f2ab5b80f773")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

merge_losses Ran
ran; our contract draft was wrong, not the code
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("3df1936cbc8f5abe")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

pairwise_distances Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("a34f75316e245682")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

QINCo Not yet run
unverified (harvested, no recorded run)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("6302cfaf7df6300e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

QINCoStep Not yet run
unverified (harvested, no recorded run)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("9796e95fac6fb501")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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.

QincoSubstep Not yet run
unverified (harvested, no recorded run)
facebookresearch/qinco/qinco/model/qinco_base.py
pointer only (licence: NOASSERTION) · get_code("112cbf1daa7d58cb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, facebookresearch/qinco (NOASSERTION). 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

Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization (RQ) is one such method, which iteratively quantizes the error of the previous step. While the error distribution is dependent on previously-selected codewords, this dependency is not accounted for in conventional RQ as it uses a fixed codebook per quantization step. In this paper, we propose QINCo, a neural RQ variant that constructs specialized codebooks per step that depend on the approximation of the vector from previous steps. Experiments show that QINCo outperforms state-of-the-art methods by a large margin on several datasets and code sizes. For example, QINCo achieves better nearest-neighbor search accuracy using 12-byte codes than the state-of-the-art UNQ using 16 bytes on the BigANN1M and Deep1M datasets.

For agents

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

get_harvested_code_for_paper("2401.14732")
get_code_for_paper("2401.14732")
have("2401.14732")

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

curl https://syntology.ai/api/ran/2401.14732.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.14732.svg)](https://syntology.ai/paper/2401.14732)

Connect an agent — have() is free.