From 1f69ee5fcb3354530fa650dd754d26077320ec16 Mon Sep 17 00:00:00 2001 From: ysun67 Date: Thu, 24 Sep 2026 00:19:43 -0400 Subject: [PATCH] Expand DOOP corpus to 21 measured applications --- docs/benchmarks.md | 79 ++++++--- examples/doop_benchmark.py | 19 +-- examples/doop_suite/datasets.json | 264 ++++++++++++++++++++++++++---- 3 files changed, 294 insertions(+), 68 deletions(-) diff --git a/docs/benchmarks.md b/docs/benchmarks.md index e03fa90..ab26481 100644 --- a/docs/benchmarks.md +++ b/docs/benchmarks.md @@ -58,26 +58,67 @@ Each invocation prints one line per phase (DSL build → emit → compile → load → run) with wall-clock timings — useful when diagnosing where time is going on your box. -## Twelve-dataset DOOP corpus +## Real-application DOOP corpus -`examples/doop_benchmark.py` prepares twelve real DaCapo +`examples/doop_benchmark.py` combines the original twelve DaCapo 23.11-MR2-chopin applications from the -[published FlowLog facts](https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/tree/main/dataset/csv). -`examples/doop_suite/datasets.json` pins the corpus revision, archive SHA-256, -archive size, and the source of the upstream reference cardinalities. -These are fresh Chopin datasets, not aliases for the older five local datasets. - -The following **local scheduling tiers** use upstream reference `VarPointsTo` -cardinality, not input size or measured SRDatalog results. They are not official -DOOP dataset editions. H2O, for example, has substantially more raw input than -Jython but a much smaller upstream points-to result. - -| Tier | Reference VPT rows | Applications | +[published FlowLog facts](https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/tree/main/dataset/csv) +with new DaCapo 2006 and independent JVM applications. +`examples/doop_suite/datasets.json` pins each archive's SHA-256, size, source +revision, and per-application provenance. The +[expansion release](https://github.com/harp-lab/srdatalog-python/releases/tag/doop-corpus-expanded-v1) +contains the new raw fact archives, extraction provenance, `measurements.json`, +and a candidate-selection audit. No binaries or facts are stored in Git. + +The **local scheduling tiers** now uniformly use measured canonical SRDatalog +CPU `VarPointsTo` cardinality, not archive size or mixed upstream analyses. +The thresholds are unchanged; these are not official DOOP dataset editions. +The original twelve archives are unchanged, and their upstream cardinalities +remain separately recorded for traceability. Every selected application has +completed the unchanged canonical CPU query with 74 relation counts and all +37 IDB exports. Zero warmups and one repetition establish cardinality evidence, +not comparative performance or GPU equivalence. + +The catalog has **21 distinct applications: 6 small, 5 medium, 6 large, 4 xlarge**, +compared with the original 5/2/4/1 distribution. + +| Tier | Canonical VPT rows | Applications | |---|---:|---| -| small | < 15 million | xalan, zxing, biojava, pmd, sunflow | -| medium | 15–<30 million | h2o, spring | -| large | 30–<100 million | batik, eclipse, fop, h2 | -| xlarge | >= 100 million | jython | +| small | < 15 million | xalan, zxing, biojava, pmd, bloat, sunflow | +| medium | 15–<30 million | clojure, chart, h2o, javac, spring | +| large | 30–<100 million | batik, eclipse, h2, fop, jruby, pdfbox | +| xlarge | >= 100 million | soot, jython, scala, kotlin | + +| New application | Version / source | Measured VPT rows | +|---|---|---:| +| bloat | DaCapo 2006 | 11,227,250 | +| chart | DaCapo 2006 | 17,221,612 | +| clojure | 1.8.0 | 16,591,860 | +| javac | OpenJDK 8u312 | 24,163,325 | +| jruby | 1.7.27 | 60,512,570 | +| pdfbox | 2.0.20 | 69,315,812 | +| soot | 4.3.0 | 412,802,921 | +| scala | 2.11.12 | 612,741,889 | +| kotlin | 1.5.31 | 1,076,040,872 | + +New inputs use DOOP 4.24.9 and `java_8`, with the container image, platform, +application and dependency hashes recorded in each provenance asset. +They preserve all extracted facts and genuine application main methods: +no multiplied facts, synthetic roots, sampled inputs, or duplicate versions +counted as new applications. Raw archive preparation was checked for byte-identical +normalized relations and metadata against the immutable CPU-validated inputs. +Recorded absolute paths in the evidence identify the original runs; portable +use goes through the catalog commands below. + +These are static extracted-fact workloads, not claims of complete Java or +reflection coverage. Phantom diagnostics are retained, not suppressed: +some name generated outer prefixes whose dollar-suffixed classes exist, while +optional missing types remain in some applications. Scala retains phantom-based +methods. Kotlin's official embeddable artifact omits shaded IntelliJ UI classes; +after supplying its dependencies, JNA and Java 8 tools, 23 phantom methods and +3 phantom-based methods remain. Consult the full provenance rather than assuming +a phantom-free corpus. Failed Soot extraction attempts were not promoted merely +because the process exited zero. Upstream software retains its own licenses. ```bash python examples/doop_benchmark.py list @@ -92,8 +133,8 @@ python examples/doop_benchmark.py prepare --tier medium \ ``` Python 3.10+ and the external `sort` command are required for preparation. -Downloading all archives requires approximately 1.74 GB; the complete raw facts -require approximately 28.3 GB before normalized inputs, dictionaries, build +Downloading all archives requires approximately 2.96 GB; the complete raw facts +require approximately 52.3 GB before normalized inputs, dictionaries, build caches or result exports. Keep all data outside the source checkout. `--archive-cache DIR` optionally reuses a read-only archive cache after checksum verification. `DOOP_SORT_TMPDIR` can select an existing scratch directory. diff --git a/examples/doop_benchmark.py b/examples/doop_benchmark.py index e4fe6ad..10fc736 100755 --- a/examples/doop_benchmark.py +++ b/examples/doop_benchmark.py @@ -1,5 +1,5 @@ #!/usr/bin/env python3 -"""Prepare and inspect the pinned twelve-application DOOP benchmark suite.""" +"""Prepare and inspect the pinned real-application DOOP benchmark suite.""" from __future__ import annotations @@ -20,7 +20,7 @@ def selection(parser: argparse.ArgumentParser, *, required: bool = True) -> None: group = parser.add_mutually_exclusive_group(required=required) - group.add_argument('--all', action='store_true', help='Select all twelve datasets') + group.add_argument('--all', action='store_true', help='Select all catalog datasets') group.add_argument('--dataset', nargs='+', metavar='NAME', help='Select named datasets') group.add_argument('--tier', choices=list(load_catalog()['tiers'])) @@ -37,21 +37,14 @@ def prepare_dataset(dataset: dict, root: Path, archive_cache: Path | None = None verify_raw(archive, dataset, raw) else: raw = extract_archive(archive, dataset, root) - catalog = load_catalog() - provenance = dict( - dataset, - corpus=catalog['corpus'], - revision=catalog['revision'], - repository=catalog['repository'], - reference_source=catalog['reference_source'], - ) + provenance = dict(dataset) return prepare(raw, output, provenance=provenance) def main(argv: list[str] | None = None) -> int: parser = argparse.ArgumentParser(description=__doc__) commands = parser.add_subparsers(dest='command', required=True) - listing = commands.add_parser('list', help='Show tiers, names and upstream reference sizes') + listing = commands.add_parser('list', help='Show tiers, names and canonical reference sizes') selection(listing, required=False) listing.add_argument('--json', action='store_true') for command in ('fetch', 'prepare'): @@ -71,9 +64,7 @@ def main(argv: list[str] | None = None) -> int: if args.json: print(json.dumps(datasets, indent=2)) else: - print( - 'Local tiers use upstream reference VarPointsTo rows, NOT input size or local results.' - ) + print('Local tiers use measured canonical VarPointsTo rows, NOT input or archive size.') print(f'{"DATASET":12} {"TIER":8} {"REFERENCE VPT":>15} {"ARCHIVE MB":>12}') for item in datasets: print( diff --git a/examples/doop_suite/datasets.json b/examples/doop_suite/datasets.json index 11908aa..77a32b4 100644 --- a/examples/doop_suite/datasets.json +++ b/examples/doop_suite/datasets.json @@ -1,12 +1,8 @@ { - "schema_version": 1, - "suite": "doop-chopin-12", - "corpus": "DaCapo 23.11-MR2-chopin", - "repository": "NemoYuu/flowlog_benchmark", - "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", - "reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", - "tier_metric": "upstream_reference_VarPointsTo_rows", - "tier_note": "Local scheduling tiers based on upstream FlowLog results, not measured SRDatalog outputs, input bytes, or official DOOP size editions.", + "schema_version": 2, + "suite": "doop-real-applications", + "tier_metric": "canonical_VarPointsTo_rows", + "tier_note": "Local scheduling tiers use measured canonical SRDatalog CPU VarPointsTo cardinality, not input bytes or official DOOP editions.", "tiers": { "small": { "min_rows": 0, @@ -29,98 +25,296 @@ { "name": "xalan", "tier": "small", - "reference_vpt_rows": 2741586, + "reference_vpt_rows": 2742413, "archive_bytes": 105440689, "archive_sha256": "fb80819fb66153b4370325cafb632ee5649917ff7e2d5b6645d6e360c61dd11f", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/xalan.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/xalan.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 2741586, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { "name": "zxing", "tier": "small", - "reference_vpt_rows": 4024065, + "reference_vpt_rows": 4036468, "archive_bytes": 72025076, "archive_sha256": "154593343fefd18306d4098ba9f6286947b134b56ebcf83d8e8eae368d5867e7", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/zxing.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/zxing.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 4024065, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { "name": "biojava", "tier": "small", - "reference_vpt_rows": 4901635, + "reference_vpt_rows": 4903555, "archive_bytes": 173260481, "archive_sha256": "6e81c27378dd151de6415ab49bb62ced9f8e70bfb69d9cd59df0a57c02091cde", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/biojava.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/biojava.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 4901635, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { "name": "pmd", "tier": "small", - "reference_vpt_rows": 8511281, + "reference_vpt_rows": 8531305, "archive_bytes": 86623764, "archive_sha256": "8825defd6500c31ac1fbc2c5b82d8f46da6a7dbd3d395b1b7de245fef4d230c9", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/pmd.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/pmd.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 8511281, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" + }, + { + "name": "bloat", + "tier": "small", + "reference_vpt_rows": 11227250, + "archive_bytes": 38367401, + "archive_sha256": "d4625f6f6cad16e999c6aaf45fe3183d3ea272a5c2cf4b639cc605922dfe6dd4", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/bloat.zip", + "corpus": "DaCapo 2006", + "application_version": "DaCapo 2006", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:d4625f6f6cad16e999c6aaf45fe3183d3ea272a5c2cf4b639cc605922dfe6dd4", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/bloat.provenance.json" }, { "name": "sunflow", "tier": "small", - "reference_vpt_rows": 11616018, + "reference_vpt_rows": 11624687, "archive_bytes": 67542238, "archive_sha256": "18641d21a7267abf19616ba12d9a39c667f15c0cd1ea8fd2c611cbe9f01ab717", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/sunflow.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/sunflow.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 11616018, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" + }, + { + "name": "clojure", + "tier": "medium", + "reference_vpt_rows": 16591860, + "archive_bytes": 78469775, + "archive_sha256": "1e23f9a6078c14be50d13e76dd1400fbc4146ac19568eaf72a8984c0d0ac9a03", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/clojure.zip", + "corpus": "Independent JVM applications", + "application_version": "1.8.0", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:1e23f9a6078c14be50d13e76dd1400fbc4146ac19568eaf72a8984c0d0ac9a03", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/clojure.provenance.json" + }, + { + "name": "chart", + "tier": "medium", + "reference_vpt_rows": 17221612, + "archive_bytes": 75959729, + "archive_sha256": "6a8cf4550780323bd9071ca8f8d53b1e0dc3be7c82107dbd58d75cc239d7a964", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/chart.zip", + "corpus": "DaCapo 2006", + "application_version": "DaCapo 2006", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:6a8cf4550780323bd9071ca8f8d53b1e0dc3be7c82107dbd58d75cc239d7a964", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/chart.provenance.json" }, { "name": "h2o", "tier": "medium", - "reference_vpt_rows": 17911631, + "reference_vpt_rows": 17930029, "archive_bytes": 681540893, "archive_sha256": "65dfd99a751a7de2d6181b6be0eaa7643e2b3303cd2b47c53187c51fa081d816", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/h2o.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/h2o.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 17911631, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" + }, + { + "name": "javac", + "tier": "medium", + "reference_vpt_rows": 24163325, + "archive_bytes": 143610050, + "archive_sha256": "aa243a006e37b665da4da91b8180851ec2423d71a6e00e101daeeb024a17895c", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/javac.zip", + "corpus": "Independent JVM applications", + "application_version": "OpenJDK 8u312", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:aa243a006e37b665da4da91b8180851ec2423d71a6e00e101daeeb024a17895c", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/javac.provenance.json" }, { "name": "spring", "tier": "medium", - "reference_vpt_rows": 25953984, + "reference_vpt_rows": 26035487, "archive_bytes": 84803735, "archive_sha256": "3ee424fb3b748c3b3f28a4841ae99d3506af37eefb6d3bb608c93e8f1519d5a8", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/spring.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/spring.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 25953984, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { "name": "batik", "tier": "large", - "reference_vpt_rows": 37237353, + "reference_vpt_rows": 37269128, "archive_bytes": 105982324, "archive_sha256": "0e66c095e6a65e765e0481bb1cc878f1d4d9845bbd11e744dea80be9470adda2", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/batik.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/batik.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 37237353, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { "name": "eclipse", "tier": "large", - "reference_vpt_rows": 39139806, + "reference_vpt_rows": 39165777, "archive_bytes": 44907723, "archive_sha256": "bae047f6d5fe1dfaa3c171516922e66ba3d2f8dd7244b43059c2ec7e6677ffc3", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/eclipse.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/eclipse.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 39139806, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" + }, + { + "name": "h2", + "tier": "large", + "reference_vpt_rows": 39881359, + "archive_bytes": 83784448, + "archive_sha256": "f9c4d90ce0868456e73bdb0b05aa6e1d9177f2feff5bd964f3dbb61c8d2c1fdf", + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/h2.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 39871906, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { "name": "fop", "tier": "large", - "reference_vpt_rows": 39818826, + "reference_vpt_rows": 39904244, "archive_bytes": 108025042, "archive_sha256": "f88c3d58fa3b5216ad49402a593676e474dc5067e87af498ed3d8f8b64eb343c", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/fop.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/fop.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 39818826, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" }, { - "name": "h2", + "name": "jruby", "tier": "large", - "reference_vpt_rows": 39871906, - "archive_bytes": 83784448, - "archive_sha256": "f9c4d90ce0868456e73bdb0b05aa6e1d9177f2feff5bd964f3dbb61c8d2c1fdf", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/h2.zip" + "reference_vpt_rows": 60512570, + "archive_bytes": 136177116, + "archive_sha256": "4a797e91359fb4e1e8b0c91045274a798065998fcb3cff8e102e62848a6a4a14", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/jruby.zip", + "corpus": "Independent JVM applications", + "application_version": "1.7.27", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:4a797e91359fb4e1e8b0c91045274a798065998fcb3cff8e102e62848a6a4a14", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/jruby.provenance.json" + }, + { + "name": "pdfbox", + "tier": "large", + "reference_vpt_rows": 69315812, + "archive_bytes": 109916260, + "archive_sha256": "77882c8af5788f8a790fdfbee5e302166f4ca307577c3fa017504a6d621a691a", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/pdfbox.zip", + "corpus": "Independent JVM applications", + "application_version": "2.0.20", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:77882c8af5788f8a790fdfbee5e302166f4ca307577c3fa017504a6d621a691a", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/pdfbox.provenance.json" + }, + { + "name": "soot", + "tier": "xlarge", + "reference_vpt_rows": 412802921, + "archive_bytes": 140643371, + "archive_sha256": "5a8b6f09e52d47b788bcd2e2fd6b0c1985c4203e129337edade88a1c86f0dec1", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/soot.zip", + "corpus": "Independent JVM applications", + "application_version": "4.3.0", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:5a8b6f09e52d47b788bcd2e2fd6b0c1985c4203e129337edade88a1c86f0dec1", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/soot.provenance.json" }, { "name": "jython", "tier": "xlarge", - "reference_vpt_rows": 438304400, + "reference_vpt_rows": 438477770, "archive_bytes": 121807572, "archive_sha256": "67c0f289eda34b05cd8226dc4e41e87d016b8ddd2ec2e0f8a8d888c555596008", - "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/jython.zip" + "url": "https://huggingface.co/datasets/NemoYuu/flowlog_benchmark/resolve/da9e91b3ff75d94604f57ba2b21ef3aa97e241ec/dataset/csv/jython.zip", + "corpus": "DaCapo 23.11-MR2-chopin", + "repository": "NemoYuu/flowlog_benchmark", + "revision": "da9e91b3ff75d94604f57ba2b21ef3aa97e241ec", + "upstream_reference_vpt_rows": 438304400, + "upstream_reference_source": "https://github.com/flowlog-rs/flowlog-bench/blob/caa5f4afb630f8c275f3ea541f628f9c58245a8d/docs/data/doop-data-prep.md", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json" + }, + { + "name": "scala", + "tier": "xlarge", + "reference_vpt_rows": 612741889, + "archive_bytes": 170647506, + "archive_sha256": "3aed6fa618bf8c543f7636b5aca76e4bcf7ca606a9ac45acad1f3d4751103a0f", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/scala.zip", + "corpus": "Independent JVM applications", + "application_version": "2.11.12", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:3aed6fa618bf8c543f7636b5aca76e4bcf7ca606a9ac45acad1f3d4751103a0f", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/scala.provenance.json" + }, + { + "name": "kotlin", + "tier": "xlarge", + "reference_vpt_rows": 1076040872, + "archive_bytes": 327922522, + "archive_sha256": "a5f7762186335d6244c04945e99dc05e28135972222d415538e4901fa9785698", + "url": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/kotlin.zip", + "corpus": "Independent JVM applications", + "application_version": "1.5.31", + "repository": "harp-lab/srdatalog-python", + "revision": "sha256:a5f7762186335d6244c04945e99dc05e28135972222d415538e4901fa9785698", + "reference_source": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/measurements.json", + "extraction_provenance": "https://github.com/harp-lab/srdatalog-python/releases/download/doop-corpus-expanded-v1/kotlin.provenance.json" } ] }