← Back to all development cases
This case was judged by an anonymized AI reviewer and has not been independently reviewed by people; inspect the draft, cards, and both outputs to assess it.
AutocompleteWith cards better41 / 280 · beu-8ddf396524cd6bed

Cosmology Intertwined: A Review of the Particle Physics, Astrophysics, and Cosmology Associated with the Cosmological Tensions and Anomalies

Astrophysics · 2203.06142v3

FLOWING EVIDENCE BENCHMARK

How do we compare writing with and without cards?

At the same writing position, the same model produces one first result with cards and one without. All 280 pairs enter the overall anonymized review, which assesses whether a decision not to continue fits the draft.

Overall: 138 with-card wins, 26 ties, 107 no-card wins, 5 pairs where neither was usable, and 4 inconclusive judgments. Both sides wrote text in 218 pairs; 48 had a deliberate stop and 14 included an invalid output.

SAME DRAFT · WITH OR WITHOUT CARDS

01 · FIXED WRITING POSITION

MANUSCRIPT

Same writing position ▌

Matched autocomplete at the same draft position

02 · TWO MATCHED VERSIONS

SHARED BY BOTH

Draft, writing task, and generation model

A · With cards

Relevant literature cards supplied

B · Without cards

No literature cards supplied

Generation model

Same model and version

A → first output

B → first output

Anonymized AI judge

First outputs are anonymized as X and Y

Continuation review: accuracy, fit to the writing task and usability
Returns: X preferred / tie / Y preferred / both unusable

Review again with the answer order swapped

HOW DOES BLIND JUDGING WORK?

① Anonymize both outputs
The AI judge sees the same draft and both first outputs without knowing which received cards.

② Compare and swap order
The judge applies task-specific criteria in X/Y and then Y/X order.

③ Review disagreements
A third pass resolves disagreements. Incomplete reviews remain in the denominator.

How are positions and cards selected?

We selected 40 writing positions in each of seven fields, for 280 comparisons. The position and relevant literature cards were set before each comparison, so both versions began from the same draft.

The main result retains every frozen position, including places where cards might not add a useful next move. This avoids selecting cases based on their outputs, but 49% describes the whole cohort, not a win rate where evidence clearly had an opportunity to help. This cohort did not record that opportunity label for each position before generation, so those two groups cannot yet be separated reliably.

CARD USE · 140/280

Reported card use in continuations with text

The model reports whether a card affected its continuation. In 140 of 280 tests it produced continuation text and reported card use. The previous count of 150 included 10 cases without continuation text and has been corrected.

COMPARISON · 70 / 7 / 30

Which written version was better?

Of the 107 reported-use cases where both versions produced text, the blinded AI judge preferred the with-card version 70 times, found 7 about the same, and preferred the without-card version 30 times.

How are the two table percentages calculated?

ADOPTION COVERAGE

140reported use with text
÷
280all positions
=
50%

WITH-CARD VERSION PREFERRED

70with cards better
÷
107comparable tests
=
65%

The percentages use different groups: 50% counts continuations with text reporting card use among all 280 tests; 65% covers the 107 such cases with text on both sides. The generating model reports card use, while an anonymized AI judge compares writing quality.

Card use is self-reported by the generator. The anonymized AI judge sees the draft and source snippets, so source-aware preference remains possible; there was no independent human review. The overall result describes these 280 frozen positions, not a win probability for any writing task.

Manuscript writing position

Text excerpt · not a PDF page

Research manuscript · excerpt

Cosmology Intertwined: A Review of the Particle Physics, Astrophysics, and Cosmology Associated with the Cosmological Tensions and Anomalies

IX Stepping Up to the New Challenges > IX.1 Future Investigations in Cosmology > IX.1.4 Cosmic Microwave Background

… error even in the era of future galaxy surveys [ 429 ] . However, strictly speaking, it is not clear by default what fiducial cosmology should be used in the BAO template. One option is to fix it by first running the full-shape analysis without the post-reconstructed BAO data. This analysis will already constrain the cosmological parameters very tightly [ 481 ] . Then the BAO template can be calculated for the best-fit full-shape cosmology. All in all, all these arguments suggest that the BAO method does not require a major modification in order to match the precision of the future datasets.

…se experiments have accumulated observations in temperature and polarization over many frequencies and extended ranges of angular scales. In particular, with the latest Planck data we have hit the limit of cosmic variance over large and intermediate scales in temperature ( Planck CMB temperature power spectrum measurements are cosmic-variance-limited for ℓ ≲ 1600 \ell\lesssim 1600 ). However, much more information can be extracted from improved small-scale temperature measurements and high-accuracy polarization data at all scales, which are the key target of the next decade’s CMB experiments.

↓ Next paragraph was generated here

The highlighted text is near the writing position. This is a layout of the evaluation input, not a PDF screenshot.

A matched comparison at the same writing positionOverall AI review: With cards better

Both arms use the same model, task and manuscript context. Only the retrieved passages differ. The first recorded output from each arm is shown below.

Read overall AI review rationale

A = without cards · B = with cards

Both outputs provide relevant continuations about future CMB experiments, but Output B is a substantially better fit for this specific position in the manuscript. The draft ends by discussing how Planck has hit cosmic variance limits in temperature at ℓ≲1600, and how 'much more information can be extracted from improved small-scale temperature measurements and high-accuracy polarization data at all scales, which are the key target of the next decade's CMB experiments.' Output B directly continues this thread by specifying what ground-based experiments will target (arcminute-scale polarization for primary anisotropies and reionization signature) and provides a concrete quantitative forecast (better than 1% accuracy for predicting primordial temperature spectrum) that naturally extends the discussion of information extraction from future data. This forecast is supported by the first source snippet about combining Advanced ACTPol small-scale E-mode data with Planck temperature data. Output A, while topically relevant, is more generic and somewhat repetitive—it lists broad science goals (neutrino masses, B-modes, dark energy) that were not the focus of the preceding paragraph. The preceding text emphasized small-scale temperature and polarization for overcoming cosmic variance limits, not primarily neutrino masses or dark energy. Output A also introduces 'Simons Observatory' without context and makes claims about 'percent-level precision' for dark energy that aren't grounded in the visible draft or sources. Output B's narrower, more precise continuation better matches the argumentative scope and would insert more seamlessly without requiring substantial repair to maintain coherence.

Evidence

Same model and position · retrieved passages supplied · first output

Preferred by blind review

Future ground-based CMB experiments will target arcminute-scale polarization to improve constraints on the primary anisotropies and the reionization signature, with forecasts indicating that combining small-scale E-mode polarization measurements with low- and intermediate-multipole temperature data can predict the underlying primordial temperature spectrum at high multipoles to better than 1% accuracy.

Passages supplied to the Evidence version

Card 1 · Precision Epoch of Reionization studies with next-generation CMB experiments

Future arcminute resolution polarization data from ground-based Cosmic Microwave Background (CMB) observations can be used to estimate the contribution to the temperature power spectrum from the primary anisotropies and to uncover the signature of reionization near ℓ = 1500 \ell=1500 in the small an…

Read full passage excerpt

Future arcminute resolution polarization data from ground-based Cosmic Microwave Background (CMB) observations can be used to estimate the contribution to the temperature power spectrum from the primary anisotropies and to uncover the signature of reionization near ℓ = 1500 \ell=1500 in the small angular-scale temperature measurements. Our projections are based on combining expected small-scale E-mode polarization measurements from Advanced ACTPol in the range 300 < ℓ < 3000 300<\ell<3000 with simulated temperature data from the full Planck mission in the low and intermediate ℓ \ell region, 2 < ℓ < 2000 2<\ell<2000 . We show that the six basic cosmological parameters determined from this combination of data will predict the underlying primordial temperature spectrum at high multipoles to better than 1 % 1\% accuracy.

Card 2 · Mitigating the optical depth degeneracy using the kinematic Sunyaev-Zel’dovich effect with CMB-S4 data

The epoch of reionization is one of the major phase transitions in the history of the universe, and is a focus of ongoing and upcoming cosmic microwave background (CMB) experiments with improved sensitivity to small-scale fluctuations. Reionization also represents a significant contaminant to CMB-de…

Read full passage excerpt

The epoch of reionization is one of the major phase transitions in the history of the universe, and is a focus of ongoing and upcoming cosmic microwave background (CMB) experiments with improved sensitivity to small-scale fluctuations. Reionization also represents a significant contaminant to CMB-derived cosmological parameter constraints, due to the degeneracy between the Thomson-scattering optical depth, $\ensuremath{\tau}$, and the amplitude of scalar perturbations, ${A}_{s}$. This degeneracy subsequently hinders the ability of large-scale structure data to constrain the sum of the neutrino masses, a major target for cosmology in the 2020s. In this work, we explore the kinematic Sunyaev-Zel'dovich (kSZ) effect as a probe of reionization, and show that it can be used to mitigate the optical depth degeneracy with high-sensitivity, high-resolution data from the upcoming CMB-S4 experiment. We discuss the dependence of the kSZ power spectrum on physical reionization model parameters, as …

Card 3 · Breaking the degeneracy between polarization efficiency and cosmological parameters in CMB experiments

Accurate cosmological parameter estimates using polarization data of the cosmic microwave background (CMB) put stringent requirements on map calibration, as highlighted in the recent results from the Planck satellite. In this paper, we point out that a model-dependent determination of polarization c…

Read full passage excerpt

Accurate cosmological parameter estimates using polarization data of the cosmic microwave background (CMB) put stringent requirements on map calibration, as highlighted in the recent results from the Planck satellite. In this paper, we point out that a model-dependent determination of polarization calibration can be achieved by the joint fit of the temperature-E-mode cross-power spectrum (TE) and E-mode auto-power spectrum (EE). This provides a valuable cross-check to band-averaged polarization efficiency measurements determined using other approaches. We demonstrate that, in $\mathrm{\ensuremath{\Lambda}}\mathrm{CDM}$, the combination of the TE and EE constrain polarization calibration with sub-percent uncertainty with Planck data and 2% uncertainty with sptpol data. We arrive at similar conclusions when extending $\mathrm{\ensuremath{\Lambda}}\mathrm{CDM}$ to include the amplitude of lensing ${A}_{\mathrm{L}}$, the number of relativistic species ${N}_{\mathrm{eff}}$, or the sum of th …

Card 4 · Small angular scale CMB anisotropies from CBI and BIMA experiments: Early universe or local structures?

The advent of high-resolution cosmic microwave background (CMB) experiments now allows studies on the temperature fluctuations at scales corresponding to a few arcminutes and below. Though the reported excess power at $l\ensuremath{\sim}2000\ensuremath{-}6000$ by CBI and BIMA is roughly consistent w…

Read full passage excerpt

The advent of high-resolution cosmic microwave background (CMB) experiments now allows studies on the temperature fluctuations at scales corresponding to a few arcminutes and below. Though the reported excess power at $l\ensuremath{\sim}2000\ensuremath{-}6000$ by CBI and BIMA is roughly consistent with a secondary contribution resulting from the Sunyaev-Zeldovich effect, this requires a higher normalization for the matter power spectrum than measured by other means. In addition to a local redshift contribution, another strong possibility for anisotropies at very small scales involves nonstandard aspects of inflationary models. To distinguish between contributions from early universe and local structures, including a potential point source contribution, and to understand the extent to which structures at low redshifts contribute to small-scale temperature anisotropies, it may be necessary to perform a combined study involving CMB and the large-scale structure. We suggest a cross correla …

Card 5 · Hemispherical variance anomaly and reionization optical depth

ABSTRACT Cosmic microwave background (CMB) full-sky temperature data show a hemispherical asymmetry in power nearly aligned with the Ecliptic, with the Northern hemisphere displaying an anomalously low variance, while the Southern hemisphere appears consistent with expectations from the best-fitting…

Read full passage excerpt

ABSTRACT Cosmic microwave background (CMB) full-sky temperature data show a hemispherical asymmetry in power nearly aligned with the Ecliptic, with the Northern hemisphere displaying an anomalously low variance, while the Southern hemisphere appears consistent with expectations from the best-fitting theory, Lambda Cold Dark Matter (ΛCDM). The low signal-to-noise ratio in current polarization data prevents a similar comparison. Polarization realizations constrained by temperature data show that in ΛCDM the lack of variance is not expected to be present in polarization data. Therefore, a natural way of testing whether the temperature result is a fluke is to measure the variance of CMB polarization components. In anticipation of future CMB experiments that will allow for high-precision large-scale polarization measurements, we study how the variance of polarization depends on ΛCDM-parameter uncertainties by forecasting polarization maps with Planck’s Markov chain Monte Carlo chains. We sh …

Model-reported card use

The model did not report that any card materially affected this completion.

No Evidence

Same model and position · no retrieved passages · first output

Not preferred in this comparison

Future CMB experiments, including ground-based observatories such as CMB-S4 and the Simons Observatory, are designed to map the polarization of the microwave sky with unprecedented sensitivity across a wide range of angular scales. These efforts aim to constrain the sum of neutrino masses, probe the physics of inflation through the detection of primordial B-modes, and test the nature of dark energy with percent-level precision.

Earlier card-use comparison

The earlier diagnostic compared only cases with reported card use and text on both sides; its scope differs from the overall AI review above.

This case does not have both with-card continuation text and a model-reported use record. It remains among all 280 tests but does not enter the reported-use comparison.

The passages are input material; their presence does not mean an output used them or that they support every claim. Draft and source passages are excerpted; no simulated scores or PDF appear here.