{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IS7ZLHZMKELPU2ONIN7CCVMCCR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"de3abae2203c9d46dcae21f263973f540a1a1c3f2218bd3058b703b51d380d80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T11:42:19Z","title_canon_sha256":"19d31b9ec02ff0248e324500b75f11f48605aa2cec69935e25d4a2fdad44f625"},"schema_version":"1.0","source":{"id":"2409.18658","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18658","created_at":"2026-07-05T09:12:39Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18658v1","created_at":"2026-07-05T09:12:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18658","created_at":"2026-07-05T09:12:39Z"},{"alias_kind":"pith_short_12","alias_value":"IS7ZLHZMKELP","created_at":"2026-07-05T09:12:39Z"},{"alias_kind":"pith_short_16","alias_value":"IS7ZLHZMKELPU2ON","created_at":"2026-07-05T09:12:39Z"},{"alias_kind":"pith_short_8","alias_value":"IS7ZLHZM","created_at":"2026-07-05T09:12:39Z"}],"graph_snapshots":[{"event_id":"sha256:7407fb71ef3327004cd0c0c6678fa3e46de568eb596ab4e6f7a7fe52da04d017","target":"graph","created_at":"2026-07-05T09:12:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.18658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale code datasets have acquired an increasingly central role in software engineering (SE) research. This is the result of (i) the success of the mining software repositories (MSR) community, that pushed the standards of empirical studies in SE; and (ii) the recent advent of deep learning (DL) in software engineering, with models trained and tested on large source code datasets. While there exist some ready-to-use datasets in the literature, researchers often need to build and pre-process their own dataset to meet specific requirements of the study/technique they are working on. This im","authors_text":"Gabriele Bavota, Ozren Dabi\\'c, Rosalia Tufano","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T11:42:19Z","title":"SEART Data Hub: Streamlining Large-Scale Source Code Mining and Pre-Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18658","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cec42220fbff727fbc8acf7c7c36c4a36b7faac785f5f23194f8ec1a2886a025","target":"record","created_at":"2026-07-05T09:12:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"de3abae2203c9d46dcae21f263973f540a1a1c3f2218bd3058b703b51d380d80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-09-27T11:42:19Z","title_canon_sha256":"19d31b9ec02ff0248e324500b75f11f48605aa2cec69935e25d4a2fdad44f625"},"schema_version":"1.0","source":{"id":"2409.18658","kind":"arxiv","version":1}},"canonical_sha256":"44bf959f2c5116fa69cd437e215582146d84c624686cb5e52ae8246094d69a67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44bf959f2c5116fa69cd437e215582146d84c624686cb5e52ae8246094d69a67","first_computed_at":"2026-07-05T09:12:39.286088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:39.286088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLRjlRaxo870DlG7Btbj91tAWIkTLd6N7IOmMPQ34iUi5zBkFlbxgdooi0/LcolnzBJR2AHkjVj7jHTIAN6UDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:39.286522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18658","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cec42220fbff727fbc8acf7c7c36c4a36b7faac785f5f23194f8ec1a2886a025","sha256:7407fb71ef3327004cd0c0c6678fa3e46de568eb596ab4e6f7a7fe52da04d017"],"state_sha256":"29517f2db075de5bfe7e2b719f77a17188706f20f64f21dbe92e71670835b00f"}