{
 "dandiset": "001933",
 "page": "dandisets/001933/",
 "generated": "2026-10-19T14:37:34+00:00",
 "caution": "A failure to reproduce is not a finding that the paper is wrong. It may be a failure of the attempt.",
 "outcome_counts": {
  "reproduced": 6,
  "partially_reproduced": 2,
  "not_reproduced": 1,
  "blocked": 0
 },
 "outcome_counts_with_outside_data": {
  "reproduced": 0,
  "partially_reproduced": 0,
  "not_reproduced": 1,
  "blocked": 0
 },
 "outcome_counts_elsewhere": {
  "reproduced": 4,
  "partially_reproduced": 3,
  "not_reproduced": 1,
  "blocked": 0
 },
 "attempts": [
  {
   "id": "001933-chen-2026-02",
   "dandiset": "001933",
   "dandiset_version": "0.260825.1457",
   "paper": "10.1038/s41467-026-75194-3",
   "paper_title": "Leucine-rich repeat kinase 2 impairs the release sites of Parkinson\u2019s disease vulnerable dopamine axons",
   "date": "2026-10-15",
   "kind": "agent",
   "accountable": "CatalystNeuro",
   "agent": {
    "harness": "Claude Code (GitHub Actions)",
    "model": "claude-opus-5-5",
    "protocol": "pilot-7"
   },
   "tier": "agent_verified",
   "entry": "001933-chen-2026",
   "entry_title": "LRRK2-G2019S and dopamine release from Anxa1+ and Calb1+ neurons (Chen, He et al. 2026)",
   "description": "Tests the findings of Chen, He et al. (2026). On dandiset 001933, which holds GRAB-DA3m fiber photometry in the dorsal striatum during optogenetic stimulation of Anxa1+ (15 mice) or Calb1+ (12 mice) SNc dopamine neurons in LRRK2-WT and LRRK2-G2019S mice, it compares evoked and spontaneous dopamine release between genotypes, per power and per mouse, and links the dandiset to the paper's published source data. The imaging, proteomics and western blots of Figures 1 to 5 are not in the dandiset; their claims are tested on the data the paper deposited on Zenodo, in PRIDE and in the BioImage Archive, and counted apart.",
   "notebooks": [
    {
     "path": "reproduce_chen_2026.ipynb",
     "title": "Reproducing Chen, He et al. (2026) from dandiset 001933",
     "executed": "notebooks/001933-chen-2026/reproduce_chen_2026.html"
    }
   ],
   "outcomes": [
    {
     "claim": "source-data-link",
     "statement": "The dandiset's recordings are those behind the paper's Figure 6 and Supplementary Figures 7 and 8, and the paper's published per-stimulation traces, evoked integrals and spontaneous transient integrals can be recomputed from them.",
     "source": "Figure 6C to 6F, Supplementary Figures 7B, 7C, 8C to 8E; Source Data (Zenodo 10.5281/zenodo.19930567)",
     "outcome": "not_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "All 27 mice of the source data are in the dandiset with the same genotype and line. The Anxa1 half links. 120 of 120 traces of Figure 6C and 479 of 480 of Supplementary Figure 7B equal the dandiset's dF/F from 1 s before onset (largest difference among matched traces 5.7e-13 in each), the evoked integrals equal the code's measure times 0.0001 for all Anxa1 records but one, and the transient counts match for 15 of 15 mice. The one miss in each is the last 4 mW stimulation of mouse 4398, whose processed series ends 0.8 s after onset. The Calb1 half does not link; 0 of 384 traces, 0 of 384 integrals and the transient counts of 1 of 12 mice match. dF/F recomputed from the raw signal with the code's processing reproduces the stored Calb1 series (largest difference 1.47 % dF/F) but not the published traces (median differences 66 to 519 % dF/F; 22 to 88 at the best background fraction per mouse). The published spontaneous values are 0.005 times the trapezoid integral of each transient divided by its number of samples (within-mouse spread of the ratio at most 2.2e-15; 15 of 15 Anxa1 mice and 0 of 12 Calb1 mice match at 1e-4), so part (4) as fixed, with integrals, matches for no mouse at either tolerance. The four parts match for 1.0, 0.609, 0.609 and 0 of their records, so the outcome is not reproduced. With the published measure in part (4) they match for 1.0, 0.609, 0.609 and 0.556, which would be partially reproduced; the criterion fixed integrals, so this is a variant. The mean dF/F over each transient comes close (13 of 15 Anxa1 mice within 1%, none within 1e-4). The Calb1 mismatch is not one of epoch or power labels; searched over all 64 epochs and 8 powers of each mouse, no epoch is within 1e-6 of any of the 384 S8D traces (closest 15.7 to 150.8 % dF/F), and against the matched epochs the per-mouse median slopes are 0.21 to 0.75 and offsets -13.8 to 16.2 % dF/F. The Figure 6E integrals match the 0.5 mW epochs (120 of 120) and none of the 4 mW ones. The published values reproduce the paper's statistics (Figure 6E p = 1.1e-20, Figure 6F p = 2.75e-177, Cohen's d 2.06 and 0.765), so the Calb1 differences come from the data, not from the paper's computation on them.",
     "deviations": [
      "The criterion fixed the integral of each spontaneous transient; the published values turned out to be 0.005 times the integral divided by the number of samples in the transient. That measure, and the mean dF/F, are shown as variants and do not change the outcome."
     ],
     "disagreed": false,
     "data": "with_inputs",
     "where": null,
     "proposed": null
    },
    {
     "claim": "fig6e-anxa1-evoked-reduced",
     "statement": "Optogenetically evoked dopamine release in the dorsolateral striatum (Anxa1+ projection region) at 0.5 mW is lower in LRRK2-G2019S than in LRRK2-WT mice (64 against 56 stimulations, p = 1.10e-20, one-tailed two-sample t-test).",
     "source": "Figure 6E (left), Results, last section",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "Light-on integrals at 0.5 mW, GS 48.8 against WT 128.0 % dF/F x s, one-tailed p = 1.16e-22 (paper 1.10e-20), Cohen's d 2.21. The code's window gives p = 1.1e-20, the paper's value. It holds at 4 mW (p = 4.08e-18), without the two GS mice given 0.33 s trains (p = 4.16e-17), and with mouse means (Welch p = 0.000434). The window chunking_index.m computes as written reverses the sign (p = 1).",
     "deviations": [
      "The integral is over each train's light-on period, as the Methods state; the paper's values come from the code's window, -0.1 to 1.0 s, shown as a variant. The baseline, which the Methods do not give, is the code's.",
      "The paper's plotting code selects power code 'h' for this panel; the panel is tested at the 0.5 mW of the legend, which the source data confirm, and 4 mW is shown as a variant."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "fig6e-anxa1-evoked-per-mouse",
     "statement": "Seven of eight individual G2019S mice show significantly reduced evoked dopamine release at 0.5 mW compared with the WT group; mouse 3743 does not.",
     "source": "Figure 6E (right) and legend; Results, last section",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "Under all four readings (Welch or Student, one- or two-tailed) 7 of 8 GS mice are below the WT group at p < 0.05/8 and 3743 is the exception (mean 125 against 128, Welch one-tailed p = 0.362). The count is the same with the code's window. Two of the seven, 3742 and 4885, received the paper's powers as 0.33 s trains, unlike every WT mouse, and their responses do not follow the labelled power; the other five significant mice were stimulated as the WT mice were.",
     "deviations": [
      "The Methods name Welch's test, the legend's p-values are one-tailed and the code runs a two-tailed Student test; all four readings are shown and all give 7."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "supp7c-anxa1-evoked-all-powers",
     "statement": "The reduction of evoked dopamine release in Anxa1 G2019S mice holds at each of the four stimulation powers, 0.1, 0.5, 1 and 4 mW (p from 1.29e-15 to 1.10e-20).",
     "source": "Supplementary Figure 7C; Results, last section",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "GS lower at all four powers, one-tailed p from 3.13e-15 to 1.16e-22 with the light-on window. With the code's window the p-values at 0.1, 0.5 and 1 mW equal the paper's (1.29e-15, 1.1e-20, 1.22e-17); at 4 mW it is 5.62e-16 against 2.39e-16, as that window, which runs to 1.0 s after onset, leaves 55 WT stimulations there (the processed series of mouse 4398 ends 0.8 s after its last onset). The Methods window keeps all 56.",
     "deviations": [
      "In the code's window variant, 55 WT stimulations at 4 mW in place of 56, as one falls at the end of a truncated series."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "fig6f-anxa1-spontaneous-reduced",
     "statement": "Spontaneous dopamine transients in the dorsolateral striatum are smaller in G2019S than in WT mice (1064 against 798 transients, p = 2.75e-177, one-tailed two-sample t-test), with 57 to 285 transients per mouse.",
     "source": "Figure 6F (left) and legend",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "The Methods' detection gives the paper's counts exactly (1064 and 798, 57 to 285 per mouse). Integrals GS 131.9 against WT 302.9 % dF/F x s, one-tailed p = 4.85e-72 (paper 2.75e-177). With the measure of the published values, 0.005 times the integral divided by the number of samples, p = 2.747e-177, the paper's value. With mouse means, Welch p = 0.0318.",
     "deviations": [
      "The integral of each transient is used, as the Methods state; the paper's values are 0.005 times the integral divided by the number of samples in the transient, shown as a variant."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "fig6f-anxa1-spontaneous-per-mouse",
     "statement": "Six of eight individual G2019S mice show significantly smaller spontaneous dopamine transients than the WT group; mice 4651 and 3743 do not.",
     "source": "Figure 6F (right) and legend; Results, last section",
     "outcome": "partially_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "By the integral 5 of 8 GS mice are below the WT group under every reading; the exceptions are 3743 (p = 0.431), 4651 (mean 417, above the WT mean of 303) and 4652 (p = 0.0128). With the paper's measure, 0.005 times the integral divided by the number of samples, the one-tailed Student test gives 6 of 8 with 3743 and 4651 as the exceptions and the legend's p-values (3742 5.28e-88, 4004 1.24e-95, 4652 6.21e-13, 4885 1.44e-49; 4651 0.00844 against 0.008); the Welch tests give 7 there. The difference from the paper comes from the measure; the paper's count follows the Student test of its legend.",
     "deviations": [
      "The integral of each transient is used, as the Methods state; the paper's measure is shown as a variant."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "supp8c-calb1-spontaneous-not-reduced",
     "statement": "In the dorsomedial striatum (Calb1+ projection region), spontaneous dopamine transients are not reduced in G2019S mice (970 against 682 transients, p = 0.98).",
     "source": "Supplementary Figure 8C; Results, last section",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "The paper's test does not find the effect, one-tailed p = 0.0509, difference of means 21.1 % dF/F x s, Cohen's d 0.085; the result sits at the threshold and is fragile. Moving either end of the exclusion window by up to 10 samples gives p from 0.0403 to 0.0792, below 0.05 in 59 of 121 windows. With the published measure (0.005 times the integral divided by the number of samples) GS are lower at p = 2.45e-09 (d 0.305), with the transient mean at p = 2.25e-09, with the code's exclusion window as written at p = 1.81e-05, and with mouse means Welch p = 0.402. The counts are within tolerance but differ from the paper's 970 and 682, and the Calb1 dF/F in the dandiset is not the one the paper analysed (source-data-link); the published values give p = 0.989.",
     "deviations": [
      "Run on the dandiset's Calb1 dF/F, which differs from the trace behind Supplementary Figure 8."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "supp8e-calb1-evoked-reduced",
     "statement": "Evoked dopamine release in the dorsomedial striatum from Calb1+ neuron stimulation is reduced in G2019S mice at each of four powers (56 against 40 stimulations per power, p from 6.45e-05 to 0.001).",
     "source": "Supplementary Figure 8E (left); Results, last section",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "GS lower at all four powers, one-tailed p from 4.38e-07 to 6.29e-10, smaller than the paper's 6.45e-05 to 0.001. The p-values differ because the dandiset's Calb1 dF/F is not the paper's (source-data-link). With one value per mouse (7 GS, 5 WT), Welch one-tailed p is 0.0424, 0.0413, 0.0726 and 0.0916 at 0.1, 0.5, 1 and 4 mW.",
     "deviations": [
      "Run on the dandiset's Calb1 dF/F, which differs from the trace behind Supplementary Figure 8."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "supp8e-calb1-few-mice-reduced",
     "statement": "Only 2 of 7 G2019S mice show reduced Calb1+ evoked dopamine release relative to the WT group.",
     "source": "Supplementary Figure 8E (right); Results, last section",
     "outcome": "partially_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "At 0.5 mW, 7 (Welch one-tailed), 6 (Welch two-tailed) and 4 (Student, either tail) of 7 GS mice are below the WT group at p < 0.05/7, against the paper's 2; the closest reading gives 4, recorded as measured. Student tests give 2 at 0.1 and 1 mW. The panel's power is not stated, and the dandiset's Calb1 dF/F is not the paper's.",
     "deviations": [
      "The legend does not state the power of the per-mouse panel; 0.5 mW was fixed before the analysis and the other powers are shown.",
      "Run on the dandiset's Calb1 dF/F, which differs from the trace behind Supplementary Figure 8."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "cohens-d-anxa1-larger",
     "statement": "The G2019S reduction of evoked release at 0.5 mW is much larger for Anxa1+ (Cohen's d = 2.05) than for Calb1+ stimulation (d = 0.76).",
     "source": "Results, last section",
     "outcome": "not_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "Anxa1 d = 2.21 is within tolerance; Calb1 d = 1.40 is not (0.684 to 0.836), and the ratio 1.58 is under the factor of 2 the criterion asks. With the code's window, 2.06 and 1.25. The paper's published integrals give 2.06 and 0.765, so the miss is consistent with the Calb1 dF/F in the dandiset not being the paper's. The Anxa1 effect is larger than the Calb1 effect at every power and window that starts by onset (ratio 1.29 to 1.74), so the direction of the paper's comparison holds, with a smaller gap.",
     "deviations": [
      "Run on the dandiset's Calb1 dF/F, which differs from the trace behind Supplementary Figure 8."
     ],
     "disagreed": false,
     "data": "dandiset",
     "where": null,
     "proposed": null
    },
    {
     "claim": "fig1d-lrrk2-enriched-vulnerable",
     "statement": "LRRK2 immunolabeling intensity is higher in Aldh1a1+ (vulnerable) than in Aldh1a1- SNc dopamine neurons (p = 0.0008).",
     "source": "Figure 1B and 1D",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "Over the 16 sections of the source data (5, 6 and 5 from three mice), LRRK2 intensity is higher in Aldh1a1+ than in Aldh1a1- neurons, 1.049 against 0.973, two-tailed unpaired Student p = 4.65e-06, Cohen's d 1.97; higher in 15 of 16 sections and in each mouse. The paper's p = 0.0008 matches a paired test over sections (0.000759) or an unpaired test of the three mouse means (0.000822), not the unpaired test over sections its legend names. Attempt -01 blocked this claim with data_missing under pilot-6, as the data are not in the dandiset; under pilot-7 it is a claim on data elsewhere and is tested.",
     "deviations": [
      "The test starts from the paper's per-section values. The images (S-BIAD2070) are matched by mouse but not segmented again, as the Methods' analysis runs in Imaris 10.1, a commercial program, with automatic thresholds."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "BioImage Archive S-BIAD2070 (images); Zenodo doi:10.5281/zenodo.19930567 (per-section values)",
     "proposed": null
    },
    {
     "claim": "fig2b-rab3-phosphorylation",
     "statement": "LRRK2 kinase inhibition with MLi-2 changes 289 phosphopeptides in striatal synaptosomes of G2019S mice, including RAB3 T86.",
     "source": "Figure 2A to 2C",
     "outcome": "not_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "On the log2 abundances as deposited, 1694 (reading a, all six values) or 1810 (reading b, two per group) phosphopeptides pass p <= 0.05 and |difference| > 0.58, against 289, and nearly all are lower with vehicle (1673 and 1785), as the samples labelled MLi-2 have higher abundances overall (median log2 17.84 to 18.12 against 17.25 to 17.47). The RAB3 T86 peptide passes (p = 0.00892) but is lower with vehicle (difference -1.31), so neither part of the criterion holds. Centring each sample on its median, a step the criterion did not fix, gives 243 and 282 peptides (282 within tolerance) and RAB3 T86 still higher with MLi-2 (difference -0.693, p = 0.0238). The paper's volcano table holds MLi-2 minus vehicle as the samples are labelled; on the 4340 peptides with all six values its difference equals that difference plus a constant to within 1.6e-06, and against vehicle minus MLi-2 the residual reaches 13. Its p-values are near those of a t-test on median-centred values but not equal (median gap in -log10 p 0.0088 Welch, 0.0161 Student). It gives 254 peptides at the legend's thresholds, and RAB3 T86 +0.688, which the legend reads as higher with vehicle. As the samples are labelled, the RAB3 T86 phosphopeptide rises after MLi-2. RAB10 T73 does not change (0.15, p = 0.775), so the data cannot tell whether the labels or the figure's direction are swapped. If the labels are swapped, the median-centred reading b gives 282 peptides and RAB3 T86 higher with vehicle (+0.693), which would reproduce the claim, so the outcome rests on a labelling question the data cannot answer. Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the PRIDE data.",
     "deviations": [
      "The criterion fixed log2 abundances without normalisation; the paper's volcano table follows median-centred values. The median-centred result is shown as a variant and does not change the outcome.",
      "The legend does not say which peptides were tested; two readings (all six values, two per group) are shown.",
      "The search (Proteome Discoverer with Byonic and Sequest, commercial) is not re-run; the test starts from the deposited abundances."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "PRIDE PXD065006",
     "proposed": null
    },
    {
     "claim": "fig2eg-prab3-increased",
     "statement": "Phosphorylation of RAB3A and RAB3C is increased in the SNc of G2019S mice and returns to WT levels with MLi-2.",
     "source": "Figure 2D to 2G",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "With contrasts on the pooled variance, Sidak-adjusted over the three pairs, GS is above WT and above GS with MLi-2 for RAB3A (p = 0.0202 and 0.00688) and RAB3C (0.00358 and 0.0415), with F = 8.593, 11.33, 14.76 and 7.398, the legend's values. GS with MLi-2 does not differ from WT (adjusted p = 0.963 and 0.622). Over two pairs the p-values are 0.0135, 0.00459, 0.00239 and 0.0279. Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the Zenodo data.",
     "deviations": [
      "The test starts from the deposited ratios; the uncropped blots are not quantified again, as the Methods do not say how bands were measured.",
      "The legend's two-way ANOVA has genotype and treatment factors on three groups; it is run as the equivalent one-way model with contrasts, which gives the legend's F values."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "Zenodo doi:10.5281/zenodo.19930567",
     "proposed": null
    },
    {
     "claim": "fig3d-rim-binds-unphosphorylated",
     "statement": "RIM1 and RIM2 bind unphosphorylated RAB3A in preference to RAB3A phosphorylated at T86, while RILPL1 and RILPL2 prefer the phosphorylated form.",
     "source": "Figure 3D to 3F",
     "outcome": "partially_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "RIM1 (Q99NE5-7) and RIM2 are higher with RAB3A (log2 differences 2.42 and 2.17, paired p = 0.00361 and 0.0124) and RILPL1 higher with p-RAB3A (-6.02, p = 9.8e-05). RILPL2 is detected in all six p-RAB3A and in none of the RAB3A pulldowns, so the criterion's paired test has no pair and does not find it higher with p-RAB3A; three of four comparisons hold. With the Methods' imputation (seeded), a variant, it is higher with p-RAB3A (-7.92, p = 1.21e-08), and the limma table gives logFC -7.58, so the data point the way of the claim for RILPL2. The paper's p-values for RIM2 and RILPL1 (0.011, 0.002) are those of the paired test on intensities without the log (0.0109, 0.0022). The deposited limma table agrees in direction for every group. Its counts at the text's p-value < 0.05 and |log2FC| >= 1 are 121 and 32; the paper's 69 and 16 are the counts at adjusted p < 0.05. Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the PRIDE data.",
     "deviations": [
      "RILPL2 has no pair for the criterion's paired test and is counted as not holding; the Methods' imputation followed by an unpaired t-test, which gives four of four, is shown as a variant.",
      "The tests use log2 intensities; the paper's p-values follow intensities without the log. Both are shown.",
      "Replicates are paired in run order, as the paper does not give the pairing."
     ],
     "disagreed": true,
     "data": "elsewhere",
     "where": "PRIDE PXD065125",
     "proposed": null
    },
    {
     "claim": "fig4d-fewer-active-zones",
     "statement": "Fewer TH+/VAMP2+ striatal synaptosomes from G2019S mice contain bassoon, and the remaining bassoon clusters are larger.",
     "source": "Figure 4D and 4E",
     "outcome": "partially_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "Part A holds. In the source data fewer TH+/VAMP2+ synaptosomes contain bassoon in GS (12.0 against 21.4 %, p = 6.38e-05; 0.000118 without the GS value under 1 %) and the bassoon area is larger (0.0862 against 0.0750 um2, p = 0.0301, the paper's value); with one value per mouse p = 0.263 and 0.474. Part B does not. The Methods' FIJI procedure as re-implemented here gives, GS against WT, 48.8 against 52.4 % with bassoon (p = 0.459) and a bassoon area of 0.0682 against 0.0696 um2 (overlap, p = 0.805) or 0.132 against 0.141 um2 (bassoon particle, p = 0.206). The re-implementation keeps a median of 183 VAMP2 particles per image against the legend's about 1000; the Default threshold alone gives a median of 1186 objects, of which the size limit keeps 193 and the circularity limit 183. Its percentages are more than twice the paper's, so part B may fail because of this attempt's segmentation, and its null result is weak evidence against the claim. The OME metadata of 165 of 168 images confirm the channel order. Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the Zenodo values and the BioImage Archive images.",
     "deviations": [
      "The FIJI procedure is re-implemented in Python (rolling ball as ImageJ shrinks it, ImageJ's Default threshold, scikit-image perimeters); it is not FIJI, and its particle counts are far below the paper's.",
      "The images cannot be matched to the published areas one by one; part B compares genotypes over the deposited images (35 GS and 39 WT for the percentage, 49 and 43 for the area, one image in each folder with nothing to measure)."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "BioImage Archive S-BIAD2074 (images); Zenodo doi:10.5281/zenodo.19930567 (per-area values)",
     "proposed": null
    },
    {
     "claim": "fig4i-rim1-reduced",
     "statement": "RIM1 is reduced in striatal synaptosomes of G2019S mice (p = 0.0245) but not in other striatal fractions or the SNc.",
     "source": "Figure 4H to 4L",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "RIM1 in synaptosomes is lower in GS, 0.206 against 0.319, two-tailed p = 0.0245 (the paper's value), Cohen's d -1.53. RIM1 in the S1 fraction (p = 0.896) and in the SNc (p = 0.936) does not differ, nor do synaptophysin (4G, p = 0.445) and the protein of 4H (p = 0.634). Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the Zenodo data.",
     "deviations": [
      "The test starts from the deposited band values; the uncropped blots are not quantified again, as the Methods do not say how bands were measured."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "Zenodo doi:10.5281/zenodo.19930567",
     "proposed": null
    },
    {
     "claim": "fig5-bassoon-vulnerable-axons",
     "statement": "Bassoon cluster density is reduced and cluster volume increased in Aldh1a1+ but not Aldh1a1- dopamine axons of G2019S mice, and the same holds in Anxa1+ axons.",
     "source": "Figure 5D, 5E, 5G and 5H",
     "outcome": "partially_reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "Five of six parts hold. With section 5 of WT mouse 1723 counted once (its four values equal those of section 4), Aldh1a1+ density is lower in GS (0.164 against 0.217) at Sidak p = 0.058, so part 1 fails; Aldh1a1- density does not differ (p = 0.713); bassoon volume is larger in GS Aldh1a1+ axons (p = 0.0425) and not in Aldh1a1- axons (p = 0.699); in Anxa1+ axons density is lower (p = 0.0374) and volume larger (p = 0.0148). As deposited, with the section twice, all six hold and the ANOVA gives the legend's numbers (5D Sidak p 0.0344, 5E 0.0385). Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the Zenodo values.",
     "deviations": [
      "The analysis starts from the per-section values; the 542 GB of SIM images (S-BIAD2071) are matched by file name and not analysed again, as the Methods' analysis runs in Imaris 10.1.",
      "One section that appears twice in the source data is counted once, as the claims file fixes; the paper counts it twice."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "BioImage Archive S-BIAD2071 (images); Zenodo doi:10.5281/zenodo.19930567 (per-section values)",
     "proposed": null
    },
    {
     "claim": "fig5j-no-axon-loss",
     "statement": "The volume occupied by TH+ fibres in the dorsal striatum does not differ between G2019S and WT mice.",
     "source": "Figure 5I and 5J",
     "outcome": "reproduced",
     "blocked_by": null,
     "notebook": "reproduce_chen_2026.ipynb",
     "notes": "The paper's test does not find a difference in TH volume, two-tailed p = 0.117 over 12 sections per genotype; GS is 7.1 % lower (0.929 against 1.000), Cohen's d -0.67. Attempt -01 blocked this claim with data_missing under pilot-6; under pilot-7 it is tested on the Zenodo values.",
     "deviations": [
      "The test starts from the per-section values; the images (S-BIAD2072) are matched by file name and not analysed again, as the Methods' analysis runs in Imaris 10.1."
     ],
     "disagreed": false,
     "data": "elsewhere",
     "where": "BioImage Archive S-BIAD2072 (images); Zenodo doi:10.5281/zenodo.19930567 (per-section values)",
     "proposed": null
    }
   ],
   "findings": [
    {
     "kind": "data_missing",
     "statement": "Still present from attempt -01. The Calb1 dF/F in the dandiset is not the trace behind Supplementary Figure 8. None of the 384 published Calb1 triggered traces is within 1e-6 of any epoch of its mouse (closest 15.7 % dF/F), none of the evoked integrals match, the transient counts match for 1 of 12 mice, and dF/F recomputed from the deposited raw signal with the published code reproduces the dandiset's series, not the paper's. The processing the paper used for Calb1 is neither deposited nor described."
    },
    {
     "kind": "other",
     "statement": "Still present from attempt -01, where it was recorded as data_missing. The dandiset holds only the fiber photometry of Figure 6 and Supplementary Figures 7 and 8. The imaging, proteomics and western blots of Figures 1 to 5 are public on Zenodo, in PRIDE and in the BioImage Archive, but neither the dandiset's description nor its related resources name those deposits."
    },
    {
     "kind": "other",
     "statement": "Still present from attempt -01. The processed series of mouse 4398 ends 0.81 s after its last onset, a 4 mW stimulation, while the paper's trace for that stimulation is complete."
    },
    {
     "kind": "metadata_error",
     "statement": "Still present from attempt -01. The OptogeneticEpochsTable description gives 8 ms on and 8 ms off for 500 ms, four powers and trains at least 20 s apart. The tables hold eight powers, two kinds of train in Anxa1 files (0.33 s and 0.51 s), and pairs of trains 15.3 s apart. Two trains have a pulse length of 0."
    },
    {
     "kind": "other",
     "statement": "Still present from attempt -01. Two Anxa1 G2019S mice (3742 and 4885) received the paper's four powers as 0.33 s trains of 9 ms pulses, while every other mouse received them as 0.51 s trains of 8 ms pulses. Neither the paper nor the dandiset says so, and in these two mice the response does not follow the labelled power."
    },
    {
     "kind": "metadata_error",
     "statement": "Still present from attempt -01. The dF/F series (FiberPhotometryResponseSeriesDfOverF) is stated in a.u.; its description and its values are percent dF/F."
    },
    {
     "kind": "metadata_error",
     "statement": "Still present from attempt -01. The archive's summary of the dandiset lists only a behavioral approach and BehavioralTimeSeries; the files hold fiber photometry and optogenetics."
    },
    {
     "kind": "selection_undocumented",
     "statement": "Still present from attempt -01. The dandiset holds the 27 mice the paper kept after excluding four on histology, and does not say that mice were left out or why."
    },
    {
     "kind": "code_mismatch",
     "statement": "Still present from attempt -01 (the repository is at the same commit). chunking_index.m computes the start of each window as trigger - fs*ti, so with ti = -1 the window starts 1 s after onset; the figures used the intended window starting 1 s before onset."
    },
    {
     "kind": "code_mismatch",
     "statement": "Still present from attempt -01. plot_results.m selects power code 'h' (4 mW) for Figure 6E; the figure, its legend and the source data are at 0.5 mW."
    },
    {
     "kind": "code_mismatch",
     "statement": "Still present from attempt -01, and made more exact. The Methods and transient_by_threshold.m give the integral of dF/F over each spontaneous transient; the published values of Figure 6F and Supplementary Figure 8C are 0.005 times the trapezoid integral divided by the number of samples in the transient (exact to 2.2e-15 in every Anxa1 mouse; attempt -01 described them as about 0.005 times the mean dF/F), and the code that computes them is not in the repository."
    },
    {
     "kind": "paper_inconsistency",
     "statement": "Still present from attempt -01. For the per-mouse comparisons of Figure 6 the Methods and the asterisks name Welch's test, the legends give one-tailed two-sample t-test p-values, and the code runs a two-tailed Student test."
    },
    {
     "kind": "other",
     "statement": "Still present from attempt -01. The paper does not cite the dandiset (none of its 99 references names DANDI); its data statement names Zenodo, PRIDE and the BioImage Archive."
    },
    {
     "kind": "paper_inconsistency",
     "statement": "New. In the synaptosome phosphoproteomics (PRIDE PXD065006, equal to Supplementary data 1) the RAB3 T86 phosphopeptide is higher in the samples labelled MLi-2 than in those labelled vehicle (median-centred log2 difference vehicle minus MLi-2 of -0.693, p = 0.0238), and the paper's volcano table holds MLi-2 minus vehicle (equal to it up to a constant within 1.6e-06 on 4340 peptides), while the Figure 2B legend reads a positive difference as higher with vehicle and the text reports less RAB3 phosphorylation with MLi-2. Either the sample labels of the deposit or the direction of Figure 2B is swapped."
    },
    {
     "kind": "paper_inconsistency",
     "statement": "New. The paper's volcano table (Supplementary data 1) gives 254 phosphopeptides at the legend's thresholds (p <= 0.05, |difference| > 0.58), where the text gives 289."
    },
    {
     "kind": "paper_inconsistency",
     "statement": "New. The text gives 69 and 16 proteins preferring RAB3A and p-RAB3A at p-value < 0.05 and |log2FC| = 1; the deposited limma table (PRIDE PXD065125) gives 121 and 32 at that p-value, and 69 and 16 at adjusted p < 0.05. The Figure 3E and 3F p-values are of paired tests on intensities without the log, which the legend does not say."
    },
    {
     "kind": "paper_inconsistency",
     "statement": "New. The Figure 1D legend gives a two-tailed unpaired t-test over 16 sections with p = 0.0008; on the source data that test gives p = 4.65e-06, and 0.0008 matches a paired test over sections or an unpaired test of the three mouse means."
    },
    {
     "kind": "other",
     "statement": "New. In the source data of Figure 5D and 5E, sections 4 and 5 of WT mouse 1723 carry the same four values to six digits, so one section appears to have been entered twice. Counted once, the Aldh1a1+ density comparison has Sidak p = 0.058 in place of 0.0344."
    },
    {
     "kind": "paper_inconsistency",
     "statement": "New. The source data and the legends differ in counts. Figure 4E has 51 G2019S areas against the legend's 57 (the source data give the legend's p = 0.0301); Figure 5E has 21 G2019S Aldh1a1+ sections against 20; and the 5E legend gives a genotype F of 1.277, the 5D value, where the data give 5.234 with the legend's p = 0.0252. One Figure 4D value (0.0766 %) is of the size of the Figure 4E areas and may have been pasted from there."
    },
    {
     "kind": "identifier_missing",
     "statement": "New. The source data of Figure 5G, 5H and 5J give one animal column holding WT IDs for both genotypes, so the G2019S animals are not identified. The BioImage Archive names them (S-BIAD2071 1019, 1020, 1022, 1052; S-BIAD2072 3243, 3246, 4120, 4369). S-BIAD2071 names a WT mouse 1923 where the source data name 1723, and two of its files carry no mouse ID. S-BIAD2074 names mice only by a number from 1 to 5 per genotype."
    },
    {
     "kind": "selection_undocumented",
     "statement": "New. The image studies hold images the figures do not use, without saying which were used. S-BIAD2070 has 7 images per mouse for Figure 1D, which has 5 or 6 sections per mouse; S-BIAD2071 has a fourth Anxa1 WT mouse (1018) not in Figure 5G and 5H; S-BIAD2072 has 64 volume images per genotype where the legend gives 96; and the synaptosome images of S-BIAD2074 differ in number per mouse from the published areas (G2019S 14, 10 and 12 images against 14, 11 and 10 areas in Figure 4D; 50 images against 51 areas in Figure 4E)."
    },
    {
     "kind": "methods_unavailable",
     "statement": "New. The image analyses of Figures 1 and 5 ran in Imaris 10.1 with automatic or manually adjusted thresholds that are not deposited, and the Methods do not say how western blot bands were quantified, so these values cannot be recomputed from the images and blots that are deposited."
    },
    {
     "kind": "metadata_error",
     "statement": "New. In BioImage Archive S-BIAD2074, the OME metadata of three images (BSN-area Export_ki4_BSN2, BSN3 and BSN4) give an excitation of 488 nm for all three channels, where the other 165 images give 488, 561 and 640 nm and the archive annotates bassoon, TH and VAMP2."
    }
   ],
   "verifications": [
    {
     "date": "2026-10-15",
     "kind": "agent",
     "by": "Independent agent run by CatalystNeuro (same harness, separate context, did not write the notebook)",
     "reviewed": "The executed notebook of the first run with the conclusion cells and the summary removed, the helper modules and the claims file, with the paper. The verifier tested double_threshold, evoked_integrals, cohens_d, twoway_anova and sidak_within on synthetic inputs, checked the column labels of the Figure 1D sheet and the OME metadata of one synaptosome image. Report in transcripts/001933/verifier-1-report.md.",
     "agreed": 17,
     "of": 18,
     "disagreements": [
      {
       "claim": "fig3d-rim-binds-unphosphorylated",
       "outcome": "partially_reproduced",
       "reason": "Cell 59: RIM1, RIM2 and RILPL1 hold under the paired test. RILPL2 has no values in the RAB3A pulldowns, so the paired test is undefined: 3 of 4. The closing decision replaces the criterion's paired test with the imputation variant for RILPL2, turning 3 of 4 into 4 of 4. RILPL2 is present in 6 of 6 p-RAB3A pulldowns and 0 of 6 RAB3A pulldowns, which supports the claim qualitatively, but the criterion's test cannot score it (problem 4)."
      }
     ]
    },
    {
     "date": "2026-10-15",
     "kind": "agent",
     "by": "Independent agent run by CatalystNeuro (same harness, separate context, did not write the notebook)",
     "reviewed": "The full executed notebook of the revised run, with its conclusion cells and summary, the helper modules, the README, this record and the claims file, with the paper. The verifier checked every Result cell, the summary, the notes and the findings against the printed outputs, viewed the overlay figure of cell 21 and checked that the round-1 reasons were stated faithfully. Report in transcripts/001933/verifier-2-report.md.",
     "agreed": 18,
     "of": 18,
     "disagreements": []
    }
   ]
  }
 ],
 "entries": [
  {
   "name": "001933-chen-2026",
   "type": "reproduction",
   "title": "LRRK2-G2019S and dopamine release from Anxa1+ and Calb1+ neurons (Chen, He et al. 2026)",
   "description": "Tests the findings of Chen, He et al. (2026). On dandiset 001933, which holds GRAB-DA3m fiber photometry in the dorsal striatum during optogenetic stimulation of Anxa1+ (15 mice) or Calb1+ (12 mice) SNc dopamine neurons in LRRK2-WT and LRRK2-G2019S mice, it compares evoked and spontaneous dopamine release between genotypes, per power and per mouse, and links the dandiset to the paper's published source data. The imaging, proteomics and western blots of Figures 1 to 5 are not in the dandiset; their claims are tested on the data the paper deposited on Zenodo, in PRIDE and in the BioImage Archive, and counted apart.",
   "dandisets": [
    "001933"
   ],
   "papers": [
    "10.1038/s41467-026-75194-3",
    "10.5281/zenodo.19930567"
   ],
   "derived_from": [],
   "notebooks": [
    {
     "path": "reproduce_chen_2026.ipynb",
     "title": "Reproducing Chen, He et al. (2026) from dandiset 001933",
     "executed": "notebooks/001933-chen-2026/reproduce_chen_2026.html"
    }
   ]
  }
 ]
}