{
  "schema_version": 1,
  "version": "2026-10-20",
  "generated": "2026-10-20",
  "site": "https://openrepro.org",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "documentation": "https://openrepro.org/data/",
  "citation": "https://openrepro.org/CITATION.cff",
  "feed": "https://openrepro.org/feed.xml",
  "mcp": "https://mcp.openrepro.org/mcp",
  "papers_listed": 7,
  "note": "One record per claim of every listed paper; every value comes from the attempt reports. deviation_over_tolerance is (observed − published) ÷ tolerance; null when untested, 'inf' or '-inf' when the tolerance was zero and the value missed.",
  "claims": [
    {
      "arxiv_id": "1708.05031",
      "paper": "Neural Collaborative Filtering",
      "claim_id": "neumf-nopre-8-hr10",
      "headline": true,
      "statement": "NeuMF trained from scratch (without pre-training) with 8 predictive factors reaches HR@10 = 0.688 on MovieLens-1M.",
      "location": "Table 2 (MovieLens rows, Factors = 8, 'Without Pre-training' HR@10 column), p. 7",
      "metric": "HR@10 of NeuMF without pre-training, 8 predictive factors, MovieLens-1M, leave-one-out with 99 sampled negatives",
      "unit": "ratio",
      "comparison": "within",
      "published": 0.688,
      "observed": 0.6848,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 12,
      "first_result_event": 38,
      "deviation_over_tolerance": -0.16,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.995349,
      "attempt_id": "arxiv-1708-05031-20261019T135218Z"
    },
    {
      "arxiv_id": "1708.05031",
      "paper": "Neural Collaborative Filtering",
      "claim_id": "neumf-nopre-8-ndcg10",
      "headline": true,
      "statement": "NeuMF trained from scratch (without pre-training) with 8 predictive factors reaches NDCG@10 = 0.410 on MovieLens-1M.",
      "location": "Table 2 (MovieLens rows, Factors = 8, 'Without Pre-training' NDCG@10 column), p. 7",
      "metric": "NDCG@10 of NeuMF without pre-training, 8 predictive factors, MovieLens-1M",
      "unit": "ratio",
      "comparison": "within",
      "published": 0.41,
      "observed": 0.4088,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 13,
      "first_result_event": 39,
      "deviation_over_tolerance": -0.06,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.997073,
      "attempt_id": "arxiv-1708-05031-20261019T135218Z"
    },
    {
      "arxiv_id": "1708.05031",
      "paper": "Neural Collaborative Filtering",
      "claim_id": "neumf-pre-8-hr10",
      "headline": true,
      "statement": "NeuMF initialised from pre-trained GMF and MLP (alpha = 0.5) with 8 predictive factors reaches HR@10 = 0.684 on MovieLens-1M.",
      "location": "Table 2 (MovieLens rows, Factors = 8, 'With Pre-training' HR@10 column), p. 7",
      "metric": "HR@10 of NeuMF with pre-training, 8 predictive factors, MovieLens-1M",
      "unit": "ratio",
      "comparison": "within",
      "published": 0.684,
      "observed": 0.6798,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 14,
      "first_result_event": 42,
      "deviation_over_tolerance": -0.21,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.99386,
      "attempt_id": "arxiv-1708-05031-20261019T135218Z"
    },
    {
      "arxiv_id": "1708.05031",
      "paper": "Neural Collaborative Filtering",
      "claim_id": "neumf-pre-8-ndcg10",
      "headline": true,
      "statement": "NeuMF initialised from pre-trained GMF and MLP (alpha = 0.5) with 8 predictive factors reaches NDCG@10 = 0.403 on MovieLens-1M.",
      "location": "Table 2 (MovieLens rows, Factors = 8, 'With Pre-training' NDCG@10 column), p. 7",
      "metric": "NDCG@10 of NeuMF with pre-training, 8 predictive factors, MovieLens-1M",
      "unit": "ratio",
      "comparison": "within",
      "published": 0.403,
      "observed": 0.4054,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 15,
      "first_result_event": 43,
      "deviation_over_tolerance": 0.12,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.005955,
      "attempt_id": "arxiv-1708-05031-20261019T135218Z"
    },
    {
      "arxiv_id": "1708.05031",
      "paper": "Neural Collaborative Filtering",
      "claim_id": "mlp3-8-hr10",
      "headline": false,
      "statement": "MLP with three hidden layers (32->16->8, embedding 16; the README's --layers [64,32,16,8]) reaches HR@10 = 0.671 on MovieLens-1M at 8 predictive factors.",
      "location": "Table 3 (MovieLens rows, Factors = 8, MLP-3 column), p. 8",
      "metric": "HR@10 of MLP-3, 8 predictive factors, MovieLens-1M",
      "unit": "ratio",
      "comparison": "within",
      "published": 0.671,
      "observed": 0.6707,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 16,
      "first_result_event": 61,
      "deviation_over_tolerance": -0.015,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.999553,
      "attempt_id": "arxiv-1708-05031-20261019T135218Z"
    },
    {
      "arxiv_id": "1708.05031",
      "paper": "Neural Collaborative Filtering",
      "claim_id": "mlp3-8-ndcg10",
      "headline": false,
      "statement": "MLP with three hidden layers reaches NDCG@10 = 0.399 on MovieLens-1M at 8 predictive factors.",
      "location": "Table 4 (MovieLens rows, Factors = 8, MLP-3 column), p. 9",
      "metric": "NDCG@10 of MLP-3, 8 predictive factors, MovieLens-1M",
      "unit": "ratio",
      "comparison": "within",
      "published": 0.399,
      "observed": 0.3979,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 17,
      "first_result_event": 62,
      "deviation_over_tolerance": -0.055,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.997243,
      "attempt_id": "arxiv-1708-05031-20261019T135218Z"
    },
    {
      "arxiv_id": "1606.00931",
      "paper": "DeepSurv",
      "claim_id": "support-cindex",
      "headline": true,
      "statement": "DeepSurv reaches test C-index 0.618308 on SUPPORT.",
      "location": "Table 1, p. 5 (DeepSurv column)",
      "metric": "test-set C-index of DeepSurv on SUPPORT",
      "unit": "C-index",
      "comparison": "within",
      "published": 0.618308,
      "observed": 0.618582,
      "tolerance": 0.01,
      "accepted_if": "within ±0.01",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 23,
      "first_result_event": 51,
      "deviation_over_tolerance": 0.0274,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000443,
      "attempt_id": "arxiv-1606-00931-20261018T225505Z"
    },
    {
      "arxiv_id": "1606.00931",
      "paper": "DeepSurv",
      "claim_id": "metabric-cindex",
      "headline": true,
      "statement": "DeepSurv reaches test C-index 0.643374 on METABRIC.",
      "location": "Table 1, p. 5 (DeepSurv column)",
      "metric": "test-set C-index of DeepSurv on METABRIC",
      "unit": "C-index",
      "comparison": "within",
      "published": 0.643374,
      "observed": 0.643492,
      "tolerance": 0.01,
      "accepted_if": "within ±0.01",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 24,
      "first_result_event": 52,
      "deviation_over_tolerance": 0.0118,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000183,
      "attempt_id": "arxiv-1606-00931-20261018T225505Z"
    },
    {
      "arxiv_id": "1606.00931",
      "paper": "DeepSurv",
      "claim_id": "gbsg-cindex",
      "headline": true,
      "statement": "DeepSurv reaches test C-index 0.668402 on Rotterdam & GBSG.",
      "location": "Table 1, p. 5 (DeepSurv column)",
      "metric": "test-set C-index of DeepSurv on Rotterdam (train) and GBSG (test)",
      "unit": "C-index",
      "comparison": "within",
      "published": 0.668402,
      "observed": 0.672011,
      "tolerance": 0.01,
      "accepted_if": "within ±0.01",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 25,
      "first_result_event": 53,
      "deviation_over_tolerance": 0.3609,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.005399,
      "attempt_id": "arxiv-1606-00931-20261018T225505Z"
    },
    {
      "arxiv_id": "1606.00931",
      "paper": "DeepSurv",
      "claim_id": "whas-cindex",
      "headline": true,
      "statement": "DeepSurv reaches test C-index 0.862620 on WHAS.",
      "location": "Table 1, p. 5 (DeepSurv column)",
      "metric": "test-set C-index of DeepSurv on WHAS",
      "unit": "C-index",
      "comparison": "within",
      "published": 0.86262,
      "observed": 0.858003,
      "tolerance": 0.01,
      "accepted_if": "within ±0.01",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 26,
      "first_result_event": 54,
      "deviation_over_tolerance": -0.4617,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.994648,
      "attempt_id": "arxiv-1606-00931-20261018T225505Z"
    },
    {
      "arxiv_id": "1606.00931",
      "paper": "DeepSurv",
      "claim_id": "sim-linear-cindex",
      "headline": false,
      "statement": "DeepSurv reaches test C-index 0.774019 on simulated linear data.",
      "location": "Table 1, p. 5 (DeepSurv column)",
      "metric": "test-set C-index of DeepSurv on the simulated linear survival data",
      "unit": "C-index",
      "comparison": "within",
      "published": 0.774019,
      "observed": 0.773885,
      "tolerance": 0.01,
      "accepted_if": "within ±0.01",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 27,
      "first_result_event": 55,
      "deviation_over_tolerance": -0.0134,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.999827,
      "attempt_id": "arxiv-1606-00931-20261018T225505Z"
    },
    {
      "arxiv_id": "1606.00931",
      "paper": "DeepSurv",
      "claim_id": "sim-nonlinear-cindex",
      "headline": false,
      "statement": "DeepSurv reaches test C-index 0.648902 on simulated nonlinear data.",
      "location": "Table 1, p. 5 (DeepSurv column)",
      "metric": "test-set C-index of DeepSurv on the simulated nonlinear (Gaussian) survival data",
      "unit": "C-index",
      "comparison": "within",
      "published": 0.648902,
      "observed": 0.645797,
      "tolerance": 0.01,
      "accepted_if": "within ±0.01",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 28,
      "first_result_event": 56,
      "deviation_over_tolerance": -0.3105,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.995215,
      "attempt_id": "arxiv-1606-00931-20261018T225505Z"
    },
    {
      "arxiv_id": "1711.10561",
      "paper": "PINNs",
      "claim_id": "burgers-l2-order",
      "headline": true,
      "statement": "A physics-informed network (9 layers x 20 neurons, N_u = 100, N_f = 10,000) solves the Burgers equation with relative L2 error of order 1e-4 (reported 6.7e-4).",
      "location": "Section 3.1, Fig. 1 caption, p. 8",
      "metric": "relative L2 error between predicted and exact u(t, x), printed by Burgers.py as Error u",
      "unit": "relative L2",
      "comparison": "at_most",
      "published": 0.00067,
      "observed": 0.002148728,
      "tolerance": 0.00603,
      "accepted_if": "at most 0.0067",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 8,
      "first_result_event": 18,
      "deviation_over_tolerance": 0.2452,
      "check_kind": "bound",
      "broad_bound": true,
      "ratio_to_published": 3.207057,
      "attempt_id": "arxiv-1711-10561-20261018T234638Z"
    },
    {
      "arxiv_id": "1711.10561",
      "paper": "PINNs",
      "claim_id": "burgers-l2-close",
      "headline": false,
      "statement": "The Burgers relative L2 error is within a factor of 2 of the reported 6.7e-4.",
      "location": "Section 3.1, Fig. 1 caption, p. 8",
      "metric": "relative L2 error printed by Burgers.py as Error u",
      "unit": "relative L2",
      "comparison": "at_most",
      "published": 0.00067,
      "observed": 0.002148728,
      "tolerance": 0.00067,
      "accepted_if": "at most 0.00134",
      "verdict": "inconsistent",
      "earlier_code_observed": null,
      "registered_event": 9,
      "first_result_event": 19,
      "deviation_over_tolerance": 2.2071,
      "check_kind": "bound",
      "broad_bound": true,
      "ratio_to_published": 3.207057,
      "attempt_id": "arxiv-1711-10561-20261018T234638Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "ag-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 92.5% test accuracy on AG News.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], AG News, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 92.5,
      "observed": 92.2,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 10,
      "first_result_event": 33,
      "deviation_over_tolerance": -1.0,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.996757,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "ag-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 91.5% test accuracy on AG News.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], AG News, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 91.5,
      "observed": 91.4,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 11,
      "first_result_event": 41,
      "deviation_over_tolerance": -0.3333,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.998907,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "sogou-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 96.8% test accuracy on Sogou News.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Sogou News, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 96.8,
      "observed": 96.7,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 12,
      "first_result_event": 34,
      "deviation_over_tolerance": -0.3333,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.998967,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "sogou-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 93.9% test accuracy on Sogou News.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Sogou News, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 93.9,
      "observed": 93.7,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 13,
      "first_result_event": 42,
      "deviation_over_tolerance": -0.6667,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.99787,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "dbpedia-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 98.6% test accuracy on DBpedia.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], DBpedia, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 98.6,
      "observed": 98.6,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 14,
      "first_result_event": 35,
      "deviation_over_tolerance": 0.0,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.0,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "dbpedia-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 98.1% test accuracy on DBpedia.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], DBpedia, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 98.1,
      "observed": 98.3,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 15,
      "first_result_event": 43,
      "deviation_over_tolerance": 0.6667,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.002039,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "yelp-p-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 95.7% test accuracy on Yelp Polarity.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Yelp Polarity, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 95.7,
      "observed": 95.7,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 16,
      "first_result_event": 36,
      "deviation_over_tolerance": 0.0,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.0,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "yelp-p-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 93.8% test accuracy on Yelp Polarity.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Yelp Polarity, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 93.8,
      "observed": 93.9,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 17,
      "first_result_event": 44,
      "deviation_over_tolerance": 0.3333,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.001066,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "yelp-f-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 63.9% test accuracy on Yelp Full.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Yelp Full, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 63.9,
      "observed": 63.9,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 18,
      "first_result_event": 37,
      "deviation_over_tolerance": 0.0,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.0,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "yelp-f-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 60.4% test accuracy on Yelp Full.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Yelp Full, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 60.4,
      "observed": 60.3,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 19,
      "first_result_event": 45,
      "deviation_over_tolerance": -0.3333,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.998344,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "yahoo-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 72.3% test accuracy on Yahoo! Answers.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Yahoo! Answers, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 72.3,
      "observed": 72.4,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 20,
      "first_result_event": 38,
      "deviation_over_tolerance": 0.3333,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.001383,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "yahoo-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 72.0% test accuracy on Yahoo! Answers.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Yahoo! Answers, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 72.0,
      "observed": 71.8,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 21,
      "first_result_event": 46,
      "deviation_over_tolerance": -0.6667,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.997222,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "amazon-f-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 60.2% test accuracy on Amazon Full.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Amazon Full, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 60.2,
      "observed": 60.2,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 22,
      "first_result_event": 39,
      "deviation_over_tolerance": 0.0,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.0,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "amazon-f-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 55.8% test accuracy on Amazon Full.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Amazon Full, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 55.8,
      "observed": 55.6,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 23,
      "first_result_event": 47,
      "deviation_over_tolerance": -0.6667,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.996416,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "amazon-p-bigram",
      "headline": true,
      "statement": "fastText with 10 hidden units and bigrams reaches 94.6% test accuracy on Amazon Polarity.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Amazon Polarity, fastText h=10 with bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 94.6,
      "observed": 94.6,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 24,
      "first_result_event": 40,
      "deviation_over_tolerance": 0.0,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.0,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "1607.01759",
      "paper": "fastText",
      "claim_id": "amazon-p-unigram",
      "headline": false,
      "statement": "fastText with 10 hidden units without bigrams reaches 91.2% test accuracy on Amazon Polarity.",
      "location": "Table 1, p. 3",
      "metric": "test accuracy [%], Amazon Polarity, fastText h=10 without bigrams",
      "unit": "percent",
      "comparison": "within",
      "published": 91.2,
      "observed": 91.1,
      "tolerance": 0.3,
      "accepted_if": "within ±0.3",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 25,
      "first_result_event": 48,
      "deviation_over_tolerance": -0.3333,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.998904,
      "attempt_id": "arxiv-1607-01759-20261018T223713Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "lambda0",
      "headline": true,
      "statement": "Before the first change point the spreading rate in Germany was 0.43 per day.",
      "location": "Abstract, p. 1",
      "metric": "posterior median of lambda_0, three-change-point model, data until 2020-04-21",
      "unit": "per day",
      "comparison": "within",
      "published": 0.43,
      "observed": 0.4275,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 7,
      "first_result_event": 31,
      "deviation_over_tolerance": -0.125,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.994186,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "lambda1",
      "headline": true,
      "statement": "After the first change point the spreading rate was 0.25 per day.",
      "location": "Abstract, p. 1",
      "metric": "posterior median of lambda_1",
      "unit": "per day",
      "comparison": "within",
      "published": 0.25,
      "observed": 0.2509,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 8,
      "first_result_event": 32,
      "deviation_over_tolerance": 0.045,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.0036,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "lambda2",
      "headline": true,
      "statement": "After the second change point the spreading rate was 0.15 per day.",
      "location": "Abstract, p. 1",
      "metric": "posterior median of lambda_2",
      "unit": "per day",
      "comparison": "within",
      "published": 0.15,
      "observed": 0.1544,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 9,
      "first_result_event": 33,
      "deviation_over_tolerance": 0.22,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.029333,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "lambda3",
      "headline": true,
      "statement": "After the third change point the spreading rate was 0.09 per day.",
      "location": "Abstract, p. 1",
      "metric": "posterior median of lambda_3",
      "unit": "per day",
      "comparison": "within",
      "published": 0.09,
      "observed": 0.0937,
      "tolerance": 0.02,
      "accepted_if": "within ±0.02",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 10,
      "first_result_event": 34,
      "deviation_over_tolerance": 0.185,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.041111,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "cp1-date",
      "headline": false,
      "statement": "The first change point occurred around March 6, 2020.",
      "location": "Abstract, p. 1",
      "metric": "posterior median date of change point 1, as day of March 2020",
      "unit": "day of March",
      "comparison": "within",
      "published": 6,
      "observed": 5.79,
      "tolerance": 2,
      "accepted_if": "within ±2",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 11,
      "first_result_event": 35,
      "deviation_over_tolerance": -0.105,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.965,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "cp2-date",
      "headline": false,
      "statement": "The second change point occurred around March 15, 2020.",
      "location": "Abstract, p. 1",
      "metric": "posterior median date of change point 2, as day of March 2020",
      "unit": "day of March",
      "comparison": "within",
      "published": 15,
      "observed": 15.22,
      "tolerance": 2,
      "accepted_if": "within ±2",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 12,
      "first_result_event": 36,
      "deviation_over_tolerance": 0.11,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.014667,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "2004.01105",
      "paper": "COVID-19 change points",
      "claim_id": "cp3-date",
      "headline": false,
      "statement": "The third change point occurred around March 23, 2020.",
      "location": "Abstract, p. 1",
      "metric": "posterior median date of change point 3, as day of March 2020",
      "unit": "day of March",
      "comparison": "within",
      "published": 23,
      "observed": 22.63,
      "tolerance": 2,
      "accepted_if": "within ±2",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 13,
      "first_result_event": 37,
      "deviation_over_tolerance": -0.185,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.983913,
      "attempt_id": "arxiv-2004-01105-20261018T033025Z"
    },
    {
      "arxiv_id": "1810.08473",
      "paper": "From Louvain to Leiden",
      "claim_id": "dblp-leiden",
      "headline": true,
      "statement": "On DBLP, the maximal modularity found by the Leiden algorithm over 10 replications of 10 iterations is 0.8387.",
      "location": "Table II, p. 6 (text p. 9)",
      "metric": "max modularity (gamma = 1) over 10 random starts x 10 iterations, Leiden, SNAP com-DBLP",
      "unit": "modularity",
      "comparison": "within",
      "published": 0.8387,
      "observed": 0.838377,
      "tolerance": 0.002,
      "accepted_if": "within ±0.002",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 10,
      "first_result_event": 29,
      "deviation_over_tolerance": -0.1615,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.999615,
      "attempt_id": "arxiv-1810-08473-20261018T013946Z"
    },
    {
      "arxiv_id": "1810.08473",
      "paper": "From Louvain to Leiden",
      "claim_id": "amazon-leiden",
      "headline": true,
      "statement": "On Amazon, the maximal modularity found by the Leiden algorithm is 0.9341.",
      "location": "Table II, p. 6 (text p. 9)",
      "metric": "max modularity (gamma = 1) over 10 random starts x 10 iterations, Leiden, SNAP com-Amazon",
      "unit": "modularity",
      "comparison": "within",
      "published": 0.9341,
      "observed": 0.934022,
      "tolerance": 0.002,
      "accepted_if": "within ±0.002",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 11,
      "first_result_event": 30,
      "deviation_over_tolerance": -0.039,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.999916,
      "attempt_id": "arxiv-1810-08473-20261018T013946Z"
    },
    {
      "arxiv_id": "1810.08473",
      "paper": "From Louvain to Leiden",
      "claim_id": "dblp-louvain",
      "headline": false,
      "statement": "On DBLP, the maximal modularity found by the Louvain algorithm is 0.8262.",
      "location": "Table II, p. 6 (text p. 9)",
      "metric": "max modularity (gamma = 1) over 10 random starts x 10 iterations, Louvain, SNAP com-DBLP",
      "unit": "modularity",
      "comparison": "within",
      "published": 0.8262,
      "observed": 0.826653,
      "tolerance": 0.002,
      "accepted_if": "within ±0.002",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 12,
      "first_result_event": 31,
      "deviation_over_tolerance": 0.2265,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000548,
      "attempt_id": "arxiv-1810-08473-20261018T013946Z"
    },
    {
      "arxiv_id": "1810.08473",
      "paper": "From Louvain to Leiden",
      "claim_id": "amazon-louvain",
      "headline": false,
      "statement": "On Amazon, the maximal modularity found by the Louvain algorithm is 0.9301.",
      "location": "Table II, p. 6 (text p. 9)",
      "metric": "max modularity (gamma = 1) over 10 random starts x 10 iterations, Louvain, SNAP com-Amazon",
      "unit": "modularity",
      "comparison": "within",
      "published": 0.9301,
      "observed": 0.929846,
      "tolerance": 0.002,
      "accepted_if": "within ±0.002",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 13,
      "first_result_event": 32,
      "deviation_over_tolerance": -0.127,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.999727,
      "attempt_id": "arxiv-1810-08473-20261018T013946Z"
    },
    {
      "arxiv_id": "1810.08473",
      "paper": "From Louvain to Leiden",
      "claim_id": "dblp-leiden-gain",
      "headline": true,
      "statement": "On DBLP, Leiden finds higher maximal modularity than Louvain (paper: +0.0125).",
      "location": "Table II, p. 6 (text p. 9)",
      "metric": "Leiden max modularity minus Louvain max modularity on DBLP",
      "unit": "modularity",
      "comparison": "at_least",
      "published": 0.0125,
      "observed": 0.011724,
      "tolerance": 0.0125,
      "accepted_if": "at least 0",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 14,
      "first_result_event": 33,
      "deviation_over_tolerance": -0.0621,
      "check_kind": "bound",
      "broad_bound": true,
      "ratio_to_published": 0.93792,
      "attempt_id": "arxiv-1810-08473-20261018T013946Z"
    },
    {
      "arxiv_id": "1810.08473",
      "paper": "From Louvain to Leiden",
      "claim_id": "amazon-leiden-gain",
      "headline": true,
      "statement": "On Amazon, Leiden finds higher maximal modularity than Louvain (paper: +0.0040).",
      "location": "Table II, p. 6 (text p. 9)",
      "metric": "Leiden max modularity minus Louvain max modularity on Amazon",
      "unit": "modularity",
      "comparison": "at_least",
      "published": 0.004,
      "observed": 0.004176,
      "tolerance": 0.004,
      "accepted_if": "at least 0",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 15,
      "first_result_event": 34,
      "deviation_over_tolerance": 0.044,
      "check_kind": "bound",
      "broad_bound": true,
      "ratio_to_published": 1.044,
      "attempt_id": "arxiv-1810-08473-20261018T013946Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "sdid-estimate",
      "headline": true,
      "statement": "The SDID estimate of the average effect of Proposition 99 on California per-capita cigarette sales over the 12 post-treatment years is -15.6 packs.",
      "location": "Table 1, p. 8",
      "metric": "SDID point estimate (synthdid_estimate on the California Prop 99 panel)",
      "unit": "packs per capita",
      "comparison": "within",
      "published": -15.6,
      "observed": -15.603828,
      "tolerance": 0.1,
      "accepted_if": "within ±0.1",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 9,
      "first_result_event": 45,
      "deviation_over_tolerance": -0.0383,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000245,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "sdid-se",
      "headline": true,
      "statement": "The placebo-method standard error of the SDID estimate is 8.4.",
      "location": "Table 1, p. 8 (placebo method, Section 5, Algorithm 4)",
      "metric": "sqrt of the placebo variance estimate for SDID",
      "unit": "packs per capita",
      "comparison": "within",
      "published": 8.4,
      "observed": 8.367993,
      "tolerance": 0.84,
      "accepted_if": "within ±0.84",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 10,
      "first_result_event": 50,
      "deviation_over_tolerance": -0.0381,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.99619,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "sc-estimate",
      "headline": true,
      "statement": "The synthetic control estimate is -19.6.",
      "location": "Table 1, p. 8",
      "metric": "SC point estimate (sc_estimate)",
      "unit": "packs per capita",
      "comparison": "within",
      "published": -19.6,
      "observed": -19.619663,
      "tolerance": 0.1,
      "accepted_if": "within ±0.1",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 11,
      "first_result_event": 46,
      "deviation_over_tolerance": -0.1966,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.001003,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "did-estimate",
      "headline": true,
      "statement": "The difference-in-differences estimate is -27.3.",
      "location": "Table 1, p. 8",
      "metric": "DID point estimate (did_estimate)",
      "unit": "packs per capita",
      "comparison": "within",
      "published": -27.3,
      "observed": -27.349111,
      "tolerance": 0.1,
      "accepted_if": "within ±0.1",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 12,
      "first_result_event": 47,
      "deviation_over_tolerance": -0.4911,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.001799,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "mc-estimate",
      "headline": false,
      "statement": "The matrix completion estimate is -20.2.",
      "location": "Table 1, p. 8",
      "metric": "MC point estimate (MCPanel nuclear-norm estimator as used in the authors code)",
      "unit": "packs per capita",
      "comparison": "within",
      "published": -20.2,
      "observed": -20.218135,
      "tolerance": 0.5,
      "accepted_if": "within ±0.5",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 13,
      "first_result_event": 48,
      "deviation_over_tolerance": -0.0363,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000898,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "difp-estimate",
      "headline": false,
      "statement": "The synthetic control with intercept (DIFP) estimate is -11.1.",
      "location": "Table 1, p. 8",
      "metric": "DIFP point estimate",
      "unit": "packs per capita",
      "comparison": "within",
      "published": -11.1,
      "observed": -11.104645,
      "tolerance": 0.1,
      "accepted_if": "within ±0.1",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 14,
      "first_result_event": 49,
      "deviation_over_tolerance": -0.0465,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000418,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "sc-se",
      "headline": false,
      "statement": "The placebo-method standard error of the SC estimate is 9.9.",
      "location": "Table 1, p. 8",
      "metric": "sqrt of the placebo variance estimate for SC",
      "unit": "packs per capita",
      "comparison": "within",
      "published": 9.9,
      "observed": 9.917426,
      "tolerance": 0.99,
      "accepted_if": "within ±0.99",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 15,
      "first_result_event": 51,
      "deviation_over_tolerance": 0.0176,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.00176,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "did-se",
      "headline": false,
      "statement": "The placebo-method standard error of the DID estimate is 17.7.",
      "location": "Table 1, p. 8",
      "metric": "sqrt of the placebo variance estimate for DID",
      "unit": "packs per capita",
      "comparison": "within",
      "published": 17.7,
      "observed": 17.740267,
      "tolerance": 1.77,
      "accepted_if": "within ±1.77",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 16,
      "first_result_event": 52,
      "deviation_over_tolerance": 0.0227,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.002275,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "mc-se",
      "headline": false,
      "statement": "The placebo-method standard error of the MC estimate is 11.5.",
      "location": "Table 1, p. 8",
      "metric": "sqrt of the placebo variance estimate for MC",
      "unit": "packs per capita",
      "comparison": "within",
      "published": 11.5,
      "observed": 11.509864,
      "tolerance": 1.15,
      "accepted_if": "within ±1.15",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 17,
      "first_result_event": 53,
      "deviation_over_tolerance": 0.0086,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 1.000858,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    },
    {
      "arxiv_id": "1812.09970",
      "paper": "Synthetic Difference-in-Differences",
      "claim_id": "difp-se",
      "headline": false,
      "statement": "The placebo-method standard error of the DIFP estimate is 9.5.",
      "location": "Table 1, p. 8",
      "metric": "sqrt of the placebo variance estimate for DIFP",
      "unit": "packs per capita",
      "comparison": "within",
      "published": 9.5,
      "observed": 9.45566,
      "tolerance": 0.95,
      "accepted_if": "within ±0.95",
      "verdict": "consistent",
      "earlier_code_observed": null,
      "registered_event": 18,
      "first_result_event": 54,
      "deviation_over_tolerance": -0.0467,
      "check_kind": "equivalence",
      "broad_bound": false,
      "ratio_to_published": 0.995333,
      "attempt_id": "arxiv-1812-09970-20261018T010328Z"
    }
  ]
}