Papers › REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning

REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning

1 Nov 2023arXiv:2311.00519archive 2025-07-28

Maxwell A. Xu, Alexander Moreno, Hui Wei, Benjamin M. Marlin, James M. Rehg

The success of self-supervised contrastive learning hinges on identifying positive data pairs, such that when they are pushed together in embedding space, the space encodes useful information for subsequent downstream tasks. Constructing positive pairs is non-trivial as the pairing must be similar enough to reflect a shared semantic meaning, but different enough to capture within-class variation. Classical approaches in vision use augmentations to exploit well-established invariances to construct positive pairs, but invariances in the time-series domain are much less obvious. In our work, we propose a novel method of using a learned measure for identifying positive pairs. Our Retrieval-Based Reconstruction (REBAR) measure measures the similarity between two sequences as the reconstruction error that results from reconstructing one sequence with retrieved information from the other. Then, if the two sequences have high REBAR similarity, we label them as a positive pair. Through validation experiments, we show that the REBAR error is a predictor of mutual class membership. Once integrated into a contrastive learning framework, our REBAR method learns an embedding that achieves state-of-the-art performance on downstream tasks across various modalities.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 10 ran (8 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 10 samples that ran have no recorded date.

maxxu05/rebar officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 10 ran (2 instrument-failed) · 10 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran; the contract check could not run
8ran
10unverified

Licence: 0 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from maxxu05/rebar. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

maxxu05/rebar official repository 20 samples, 10 ran (2 instrument-failed) · 10 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 3, kind float, dtype float32
models/REBAR/REBAR_SSLModel.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 032b67e962be8a73 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DilatedConvEncoder in 8 papers models/REBAR/REBAR_SSLModel.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · d8ef63e77b9e62e8 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
PartialConv1d models/REBAR/REBAR_SSLModel.py ran MIT (permissive) · 5c264d8180b9ea93 · report fixture: signature input:Tensor/3/float, mask_in:NoneType/0/? · returned Tensor · level recorded 2026-09-24
REBAR_CrossAttn_Config models/REBAR/REBAR_SSLModel.py ran MIT (permissive) · 1c9448d608e6c3c8 · report fixture: signature run_dir:str/0/str, subseq_size:int/0/int, device:str/0/str, input_dims:int/0/int · returned NoneType · level recorded 2026-09-24
RevIN in 13 papers models/REBAR/REBAR_SSLModel.py ran · metamorphic tier: invariant MIT (permissive) · 5682c8bbc83e0654 · report fixture: signature x:Tensor/3/float, mode:str/0/str, recalc_stats:bool/0/bool · returned Tensor · level recorded 2026-09-22
SamePadConv in 6 papers models/REBAR/REBAR_SSLModel.py ran fingerprinted MIT (permissive) · cb26426b6abfe2d3 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
TSEncoder in 5 papers models/REBAR/REBAR_SSLModel.py ran fingerprinted MIT (permissive) · 5ac764d53a53c6ea · report fixture: signature x:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
contrastive_loss_imp models/REBAR/REBAR_SSLModel.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · da59efe85eb510fd · report fixture: signature z1:Tensor/3/float, z2:Tensor/3/float, labels:Tensor/1/int, tau:float/0/float, alpha:float/0/float · returned Tensor · level recorded, date not recorded
instance_contrastive_loss_imp models/REBAR/REBAR_SSLModel.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 52094c3be8d651d0 · report fixture: signature z1:Tensor/3/float, z2:Tensor/3/float, labels:Tensor/1/int, tau:float/0/float · returned Tensor · level recorded, date not recorded
rebarcrossattn_maskdataset models/REBAR/REBAR_SSLModel.py ran fingerprinted MIT (permissive) · c36a648ab5d202e3 · report fixture: signature idx:int/0/int · returned tuple · level recorded 2026-09-24
BaseModelClass models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · bdb1d98d6919b1e5 · report
Base_ExpConfig models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 6c78dfb252a62051 · report
REBAR models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 0c1056dec45ae563 · report
REBARCrossAttn_SSLModel models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · afef9af0260b617c · report
REBAR_CrossAttn_Trainer models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 048bc33d3e7220e9 · report
REBAR_ExpConfig models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 2d001c071ada228b · report
dilated_conv_block models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 043a6f17d3a20a2f · report
dilated_conv_net models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 04d4a41a1d4750ea · report
printlog models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · d9a0d378a8f04f69 · report
temporal_contrastive_loss_imp models/REBAR/REBAR_SSLModel.py unverified MIT (permissive) · 47a35796faef934f · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for REBAR (graph method: REBAR). 20 bricks; individually on a fixture: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified. The assembly has not been run end-to-end.

  1. REBAR entry · level 0 · unverified · 0c1056dec45ae563
  2. BaseModelClass helper · level 0 · unverified · bdb1d98d6919b1e5
  3. REBAR_CrossAttn_Trainer helper · level 0 · unverified · 048bc33d3e7220e9
  4. REBAR_ExpConfig helper · level 0 · unverified · 2d001c071ada228b
  5. contrastive_loss_imp loss · level 1 · ran; the contract check could not run (RAISES) · da59efe85eb510fd
  6. Base_ExpConfig helper · level 0 · unverified · 6c78dfb252a62051
  7. TSEncoder model · level 1 · ran · 5ac764d53a53c6ea
  8. printlog helper · level 0 · unverified · d9a0d378a8f04f69
  9. REBARCrossAttn_SSLModel helper · level 0 · unverified · afef9af0260b617c
  10. REBAR_CrossAttn_Config helper · level 1 · ran · 1c9448d608e6c3c8
  11. rebarcrossattn_maskdataset helper · level 1 · ran · c36a648ab5d202e3
  12. instance_contrastive_loss_imp loss · level 1 · ran; the contract check could not run (RAISES) · 52094c3be8d651d0
  13. temporal_contrastive_loss_imp loss · level 0 · unverified · 47a35796faef934f
  14. DilatedConvEncoder model · level 1 · ran · d8ef63e77b9e62e8
  15. RevIN helper · level 1 · ran · 5682c8bbc83e0654
  16. dilated_conv_net helper · level 0 · unverified · 04d4a41a1d4750ea
  17. ConvBlock helper · level 1 · ran · 032b67e962be8a73
  18. dilated_conv_block helper · level 0 · unverified · 043a6f17d3a20a2f
  19. SamePadConv helper · level 1 · ran · cb26426b6abfe2d3
  20. PartialConv1d helper · level 1 · ran · 5c264d8180b9ea93

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2311.00519") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningRetrievalTime Series

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections