RED-2400: A Public Benchmark of Algorithmically-Rejected Trading Events with Outcome Labels

Arati U. Kamat

arxiv: 2605.12151 · v2 · pith:KW3YGGB6new · submitted 2026-05-12 · 💱 q-fin.TR · q-fin.CP· q-fin.ST

RED-2400: A Public Benchmark of Algorithmically-Rejected Trading Events with Outcome Labels

Arati U. Kamat This is my paper

Pith reviewed 2026-06-30 22:10 UTC · model grok-4.3

classification 💱 q-fin.TR q-fin.CPq-fin.ST

keywords public benchmarkrejected trading eventsSolana DEXoutcome labelsprice trajectorylifecycle trackingtrading filter

0 comments

The pith

RED-2400 releases a public benchmark of 6,660 rejected trading events from a live Solana DEX, each tied to its post-rejection price and liquidity path plus five-tier outcome labels.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents RED-2400 as the first public dataset drawn from a live Solana decentralized-exchange filter stack, capturing 6,660 algorithmically rejected events across 22 days along with 169,123 forward price-and-liquidity observations. Each event carries one of five outcome labels and is supported by a lifecycle-tracker file that records token ground truth. Filter identities and volume figures are anonymized or quantized to allow external use while protecting operational details. Subsequent windows are planned to extend the time series and support regime-stratified comparisons. A reader would care because the deposit supplies open, labeled trading-filter data that is normally unavailable outside proprietary systems.

Core claim

RED-2400 is a public benchmark of 6,660 algorithmically-rejected trading events from a live Solana decentralised-exchange filter stack, observed continuously over 22 calendar days, each linked to its post-rejection price-and-liquidity trajectory with five-tier outcome labels. The deposit contains 169,123 forward-outcome observations and 1,837 graveyard-tracker lifecycle snapshots covering 1,076 distinct mints, with a lifecycle-tracker file that permits external validation of any subset of those labels against observed token-lifecycle ground truth.

What carries the argument

The lifecycle-tracker file that records token ground truth and permits external validation of the five-tier outcome labels.

If this is right

External researchers can validate or correct any chosen subset of the five-tier labels using the provided lifecycle snapshots.
The dataset supplies the first time window needed for later regime-stratified analysis across multiple collection periods.
Quantized liquidity and volume fields preserve distributional shape while blocking inference of exact operational thresholds.
The structure supports analysis across 1,076 distinct mints with linked forward observations.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Later windows in the planned series could be combined to test whether rejection-outcome distributions shift with market conditions.
The anonymized filter labels allow comparative studies of rejection patterns without revealing proprietary stack details.

Load-bearing premise

The five-tier outcome labels assigned by the classification rule correctly reflect actual post-rejection price and liquidity trajectories without systematic bias from anonymization or quantization.

What would settle it

A direct comparison, on any non-empty subset of events, between the assigned five-tier labels and the independent token-lifecycle observations recorded in the graveyard-tracker snapshots.

Figures

Figures reproduced from arXiv: 2605.12151 by Arati U. Kamat.

**Figure 1.** Figure 1: Distribution of rejection events across the eight anonymised filter labels. The top five filters (filter_1 to filter_5) account for 93.4 percent of all rejections; filter_6 to filter_8 carry the remaining 6.6 percent. Counts and within-cohort percentages are annotated to the right of each bar. Filter labels are anonymised; the active scanner configuration during the observation window comprised eight filte… view at source ↗

**Figure 2.** Figure 2: Distribution of post-rejection observation age (ageMin). The interquartile range is concentrated around the median of 686 minutes (≈ 11.4 hours). The outcome time series for a typical rejected token covers roughly half of the 24-hour observation horizon. Right-censoring at 1,440 minutes (24 hours) marks the dataset cutoff for early-death classification [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗

**Figure 3.** Figure 3: Liquidity and 24-hour trade-volume distribution for the rejected-token cohort. Both fields use a log scale. The gap between median and mean (red diamond) shows heavy-tailed structure. The bulk of rejected tokens trade with liquidity below USD 50,000. The filter is rejecting low-conviction venue activity. Experimental Design, Materials and Methods I logged decision events from public Solana DEX venues conti… view at source ↗

read the original abstract

RED-2400 is a public benchmark of 6,660 algorithmically-rejected trading events from a live Solana decentralised-exchange filter stack, observed continuously over 22 calendar days (2026-04-10T21:10Z through 2026-05-02T21:48Z, UTC). Each rejection event is linked to its post-rejection price-and-liquidity trajectory. The deposit contains 169,123 forward-outcome observations and 1,837 graveyard-tracker lifecycle snapshots, covering 1,076 distinct mints in the rejection registry and 1,075 in the forward-observation file. Outcome labels follow the five-tier classification rule introduced by a related methodology paper [Kamat 2026c]. The deposit includes a lifecycle-tracker file that permits external validation of any subset of those labels against observed token-lifecycle ground truth. Filter labels are anonymised to filter_1 through filter_8; source-collector identifiers to source_a and source_b. Liquidity and 24-hour volume are quantised to the nearest power of two, preserving heavy-tailed shape while preventing operational-threshold inference. This is the first window of a planned series; subsequent windows will extend the time horizon and enable regime-stratified analysis. "RED-2400" is a brand name, not a count; current cohort sizes are listed below and do not equal 2,400.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a data-release paper putting out a new benchmark of 6,660 rejected Solana DEX trades with linked trajectories, five-tier labels, and a validation tracker file.

read the letter

The core contribution is the RED-2400 deposit itself: 6,660 events from one live Solana filter stack over 22 days, each tied to post-rejection observations, with labels assigned by the rule from the author's earlier methodology paper. The anonymized filter names, quantized liquidity and volume values, and the lifecycle-tracker file that lets outsiders check labels against ground truth are all disclosed up front. That tracker is the practical addition here; it turns the release into something externally verifiable rather than just a black-box dump.

The paper does what a data note should do: it describes the collection window, the mint coverage, the forward-observation counts, and the planned follow-on windows without claiming new theory or fitted results. The quantization choice is explained as preserving shape while blocking threshold inference, which is a reasonable engineering decision.

The limits are straightforward. Everything is confined to a single DEX ecosystem and a short calendar slice, so the benchmark only supports narrow testing of similar filters. No error rates, label-consistency checks, or sample verification appear in the text; those would have to be done by users with the files. The labeling rule is imported wholesale, so any weaknesses in that prior work travel with the dataset. This is not a flaw in execution, just the nature of a first-window release.

Researchers building or stress-testing rejection logic on Solana-style venues would get direct use from the files and tracker. A referee could usefully confirm that the supplied data matches the described counts and that the tracker actually enables the claimed validation. I would send it to review rather than desk-reject; the artifact is new and the documentation is transparent enough to evaluate on its own terms.

Referee Report

0 major / 2 minor

Summary. The manuscript presents RED-2400 as a public benchmark dataset of 6,660 algorithmically-rejected trading events from a live Solana decentralized exchange filter stack, collected continuously over 22 calendar days from 2026-04-10T21:10Z to 2026-05-02T21:48Z. Each event is linked to its post-rejection price-and-liquidity trajectory, yielding 169,123 forward-outcome observations and 1,837 graveyard-tracker lifecycle snapshots across 1,076 distinct mints. The dataset applies five-tier outcome labels according to the rule from the related methodology paper [Kamat 2026c], includes a lifecycle-tracker file for external validation, anonymizes filter labels as filter_1 to filter_8 and sources as source_a and source_b, and quantizes liquidity and 24-hour volume to the nearest power of two. It is positioned as the first in a planned series of releases.

Significance. This data release contributes a novel public benchmark for studying algorithmic trading rejections in decentralized finance, particularly on Solana. The linkage of rejection events to forward trajectories and the provision of a validation tracker file enable researchers to independently assess label accuracy and analyze post-rejection dynamics. Such resources are scarce in the field and could support the development of better filter designs, risk assessment models, and empirical studies of market microstructure in crypto exchanges. The anonymization and quantization choices are transparently motivated to preserve analytical utility while protecting operational details.

minor comments (2)

[Abstract] The abstract states that current cohort sizes are listed below but does not display the actual numbers or table in the provided text; the full manuscript should ensure this information appears explicitly to match the claim.
The manuscript refers to 'the deposit' without specifying the repository, DOI, or access URL; adding this detail would improve usability for readers.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive evaluation of the manuscript and for recommending acceptance. The summary accurately captures the dataset's scope, construction, and intended use as the first in a planned series of releases.

Circularity Check

0 steps flagged

No significant circularity; data-release paper with no derivations

full rationale

This is a descriptive data-release manuscript with no equations, fitted parameters, predictions, or derivation chain. The sole citation to [Kamat 2026c] supplies the external five-tier labeling rule and is accompanied by an explicit lifecycle-tracker file for independent validation of labels against ground truth. No step reduces to its own inputs by construction, self-definition, or self-citation load-bearing. The paper's central claim is the public release of the RED-2400 dataset and supporting files, which stands independently of any internal derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical model, derivation, or statistical fitting is present; the paper is a data release with no free parameters, axioms, or invented entities required for a central claim.

pith-pipeline@v0.9.1-grok · 5790 in / 1189 out tokens · 19331 ms · 2026-06-30T22:10:45.736718+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Reference graph

Works this paper leans on

2 extracted references · 2 canonical work pages

[1]

Kamat, Outcome-Classified Precision Auditing of Filter Rules in Algorithmic DEX Trading: Evidence from 2,400 Rejection Events (v2 forthcoming)

A. Kamat, Outcome-Classified Precision Auditing of Filter Rules in Algorithmic DEX Trading: Evidence from 2,400 Rejection Events (v2 forthcoming). 2026. SSRN abstract_id 6638259; companion deposit at Zenodo DOI 10.5281/zenodo.19987695. [Kamat 2026c]

work page doi:10.5281/zenodo.19987695 2026
[2]

Kamat, Post-Rejection Follow-up Sampling: A Methodology for Counterfactual Outcome Measurement in Algorithmic DEX Trading (v2 2026-05-30)

A. Kamat, Post-Rejection Follow-up Sampling: A Methodology for Counterfactual Outcome Measurement in Algorithmic DEX Trading (v2 2026-05-30). 2026. SSRN abstract_id 6607301; companion deposit at Zenodo DOI 10.5281/zenodo.20043516. [Kamat 2026b] Version History 2.0 (2026-05-30): Current version. Companion dataset at Zenodo DOI 10.5281/zenodo.19989075. 1.0 ...

work page doi:10.5281/zenodo.20043516 2026

[1] [1]

Kamat, Outcome-Classified Precision Auditing of Filter Rules in Algorithmic DEX Trading: Evidence from 2,400 Rejection Events (v2 forthcoming)

A. Kamat, Outcome-Classified Precision Auditing of Filter Rules in Algorithmic DEX Trading: Evidence from 2,400 Rejection Events (v2 forthcoming). 2026. SSRN abstract_id 6638259; companion deposit at Zenodo DOI 10.5281/zenodo.19987695. [Kamat 2026c]

work page doi:10.5281/zenodo.19987695 2026

[2] [2]

Kamat, Post-Rejection Follow-up Sampling: A Methodology for Counterfactual Outcome Measurement in Algorithmic DEX Trading (v2 2026-05-30)

A. Kamat, Post-Rejection Follow-up Sampling: A Methodology for Counterfactual Outcome Measurement in Algorithmic DEX Trading (v2 2026-05-30). 2026. SSRN abstract_id 6607301; companion deposit at Zenodo DOI 10.5281/zenodo.20043516. [Kamat 2026b] Version History 2.0 (2026-05-30): Current version. Companion dataset at Zenodo DOI 10.5281/zenodo.19989075. 1.0 ...

work page doi:10.5281/zenodo.20043516 2026