{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FB2JCOWNL32Q3QAYF4QDCAPEVU","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":"5360800b19c214ecdb2331538be55d9c4a6335c634182b6aa987f239e19bace3","cross_cats_sorted":["cs.DL","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-10-16T07:51:37Z","title_canon_sha256":"9d6423b0e1b222d4902c52124774698230189171188125a07cae5d57ea12f8b4"},"schema_version":"1.0","source":{"id":"1910.09313","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.09313","created_at":"2026-07-05T00:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"1910.09313v1","created_at":"2026-07-05T00:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09313","created_at":"2026-07-05T00:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"FB2JCOWNL32Q","created_at":"2026-07-05T00:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"FB2JCOWNL32Q3QAY","created_at":"2026-07-05T00:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"FB2JCOWN","created_at":"2026-07-05T00:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:c2523497247ff06dedc3b99a19a4cef18a0a931af67664eb8eda19b6f20360d9","target":"graph","created_at":"2026-07-05T00:13:32Z","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/1910.09313/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated classification of metadata of research data by their discipline(s) of research can be used in scientometric research, by repository service providers, and in the context of research data aggregation services. Openly available metadata of the DataCite index for research data were used to compile a large training and evaluation set comprised of 609,524 records, which is published alongside this paper. These data allow to reproducibly assess classification approaches, such as tree-based models and neural networks. According to our experiments with 20 base classes (multi-label classifica","authors_text":"Dieter Kranzlm\\\"uller, Michael Fromm, Nelson Tavares de Sousa, Tobias Weber","cross_cats":["cs.DL","cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-10-16T07:51:37Z","title":"Using Supervised Learning to Classify Metadata of Research Data by Discipline of Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09313","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":"sha256:1ac7f0e015bdab183712088c00c6d217617bf1b7c1bc941f521c725fc60bb171","target":"record","created_at":"2026-07-05T00:13:32Z","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":"5360800b19c214ecdb2331538be55d9c4a6335c634182b6aa987f239e19bace3","cross_cats_sorted":["cs.DL","cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-10-16T07:51:37Z","title_canon_sha256":"9d6423b0e1b222d4902c52124774698230189171188125a07cae5d57ea12f8b4"},"schema_version":"1.0","source":{"id":"1910.09313","kind":"arxiv","version":1}},"canonical_sha256":"2874913acd5ef50dc0182f203101e4ad10319b4cf2e0efdc972b01df3e0c38ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2874913acd5ef50dc0182f203101e4ad10319b4cf2e0efdc972b01df3e0c38ad","first_computed_at":"2026-07-05T00:13:32.601890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:32.601890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sxbGyzmpLjMSu+e6v5mhfXlJxQ6vRdw9oyVLiiS8w2BZUxDnmQxMikKsdsZRGVhttWYG9c4C7O0wTcMiIXdwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:32.602340Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.09313","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ac7f0e015bdab183712088c00c6d217617bf1b7c1bc941f521c725fc60bb171","sha256:c2523497247ff06dedc3b99a19a4cef18a0a931af67664eb8eda19b6f20360d9"],"state_sha256":"8a97e7232bde81e9afcdb9a86790ae34ade716b96dfd72b20540fd025537905a"}