d²Second
Derivation

BATCH release-batch-001 · 0.1.0-rc5

First review collection

Ten scoped reviews of cosmology and gravitation papers: reproduced results, bounded attempts and narrowly supported findings.

Selected cases from the project intake; not a representative sample, error-rate estimate or AI leaderboard. Each outcome applies only to the fixed reviewed version and declared scope.

10 papers · 3 Reproduced in scope · 2 Partly reproduced · 1 Confirmed finding · 2 Attempt documented · 2 Technical finding — not externally confirmed

Previous release: 0.1.0-rc4

Changes in this release
What these results mean

Technical finding — not externally confirmed

0704.0175v2 · review 0.1.0-rc3

Solar System Constraints on Gauss-Bonnet Mediated Dark Energy

The printed gravitational potentials imply a Doppler coefficient 35 times smaller, weakening the paper’s approximate coupling bound by √35.

Limit arXiv v2 only. No new Cassini-data confidence limit, journal-equation verification, or external confirmation.

OpenAI Codex + Anthropic Claude 122.1M tokens processed 7.4 h recorded session time (includes waits)

Partial records · 16/16 sessions with complete token counts · 2/16 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Reproduced in scope

2404.08056v3 · review 0.2.0-rc3

Interpreting DESI's evidence for evolving dark energy

The pivot transformation and main interpretation reproduce, with qualifications to the precision and direction of prior effects.

Limit The Dark Energy Survey five-year supernova sample does not meet the stated pivot precision; effects depend on the chosen prior.

OpenAI Codex + Anthropic Claude 74.4M tokens processed 14.5 h recorded session time (includes waits)

Partial records · 6/6 sessions with complete token counts · 6/6 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Reproduced in scope

2404.08633v3 · review 0.2.0-rc3

Does DESI 2024 Confirm ΛCDM?

The selected DESI distance fits reproduce, with small qualifications and one narrowly missed numerical tolerance.

Limit Rounded inputs and priors matter. The refitted DESI–supernova tension is 2.802σ rather than 2.7σ, narrowly outside the review tolerance.

OpenAI Codex + Anthropic Claude 85.9M tokens processed 4.1 h recorded session time (includes waits)

Partial records · 13/13 sessions with complete token counts · 11/13 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Attempt documented

2407.02558v2 · review 0.1.0-rc2

Modified gravity interpretation of the evolving dark energy in light of DESI data

The review supports selected parameter shifts and their attribution to baryon acoustic oscillation measurements, with numerical exceptions and an unfinished modified-gravity fit.

Limit One interval width and tracer amplitude miss tolerance; storage failure stopped the modified-gravity fit before usable parameter samples were retained.

OpenAI Codex + Anthropic Claude 147.6M tokens processed 51.1 h recorded session time (includes waits)

Partial records · 17/17 sessions with complete token counts · 16/17 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Technical finding — not externally confirmed

2407.15832v2 · review 0.2.0-rc2

Hints of Nonminimally Coupled Gravity in DESI 2024 Baryon Acoustic Oscillation Measurements

Saved evidence supports a conditional normalization mismatch and challenges the broad necessity inference.

Limit No external confirmation; the original one-function posterior remains unresolved, and full-likelihood impact is unknown.

OpenAI Codex + Anthropic Claude 115.3M tokens processed 16.1 h recorded session time (includes waits)

Partial records · 8/8 sessions with complete token counts · 8/8 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Attempt documented

2407.16689v2 · review 0.1.0-rc2

Robust Preference for Dynamical Dark Energy in DESI BAO and SN Measurements

Algebra and selected parameter summaries reproduce. Checks of the exponential dark-energy model and logarithmic-model probability tails remain unresolved.

Limit Supernova parameter agreement and precision with the full Planck likelihood remain unmet for the exponential model. Causes are unresolved; further computation is paused.

OpenAI Codex + Anthropic Claude 93.6M tokens processed 18.0 h recorded session time (includes waits)

Partial records · 6/6 sessions with complete token counts · 6/6 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Reproduced in scope

2408.07175v3 · review 0.2.0-rc3

Evolving Dark Energy or Supernovae Systematics?

The supernova fits and common-sample magnitude offset reproduce under the inferred distance convention and stated prior variants.

Limit The offset does not establish a full-sample calibration error; correlated cross-catalogue systematic uncertainty remains unmeasured.

OpenAI Codex + Anthropic Claude 99.5M tokens processed 5.0 h recorded session time (includes waits)

Partial records · 8/8 sessions with complete token counts · 8/8 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Confirmed finding

2501.15927v3 · review 0.1.0-rc2

Observational implications of Wald-Gauss-Bonnet topological dark energy

The author confirmed the denominator coefficient error in equation (19) and its implementation in the public CLASS cosmology code.

Limit Confirmation covers this local coefficient error; effects on cosmological inference and the complete corrected implementation remain unverified.

OpenAI Codex + Anthropic Claude 37.1M tokens processed 1.9 h recorded session time (includes waits)

Partial records · 10/10 sessions with complete token counts · 0/10 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Partly reproduced

2607.13009v1 · review 0.2.0-rc3

Model-Independent Indication for a Localized Anomaly in the Late-Time Expansion History

The pressure–distance equations and null-energy-condition identities reproduce. Numerical agreement depends on our particular reconstruction implementation.

Limit The headline significance and location remain unverified. Our reconstruction was repaired after inspecting earlier results; equivalence to the authors' pipeline is unestablished.

OpenAI Codex + Anthropic Claude 41.9M tokens processed 4.5 h recorded session time (includes waits)

Partial records · 3/5 sessions with complete token counts · 1/5 with activity time recorded

OpenAI Codex · model not recorded · reasoning: not recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner

Partly reproduced

2609.40176v1 · review 0.1.0-rc2

Is DESI Seeing Dynamical Dark Energy, or a Cosmic Glitch in Gravity?

Checked equations and printed numerical conversions agree with the paper.

Limit The headline cosmic-microwave-background inference was not rerun; its correctness is not established by these equation and arithmetic checks.

OpenAI Codex + Anthropic Claude 10.2M tokens processed 18 min recorded session time (includes waits)

Partial records · 3/4 sessions with complete token counts · 1/4 with activity time recorded

OpenAI Codex · gpt-6-astra · reasoning: high

Anthropic Claude · claude-opus-5-5 · reasoning: high · settings reported by the project owner