{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MNCP5NJH7KSW7W46IHN7X5SXKT","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":"52a0c3d32611c9bd0b71a5a22ea2ab6c159cd968810fff06daf22745064f0f94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T03:47:03Z","title_canon_sha256":"1405d5cbfff695e1f41d0655fe9707db92fb36ed14159fa15b1f0eab668d91a2"},"schema_version":"1.0","source":{"id":"1908.05758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05758","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05758v1","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05758","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_12","alias_value":"MNCP5NJH7KSW","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_16","alias_value":"MNCP5NJH7KSW7W46","created_at":"2026-07-04T23:57:52Z"},{"alias_kind":"pith_short_8","alias_value":"MNCP5NJH","created_at":"2026-07-04T23:57:52Z"}],"graph_snapshots":[{"event_id":"sha256:15b91484e576ef15e71069e511a06f0db39b1391a33083376c775d2a7b60216b","target":"graph","created_at":"2026-07-04T23:57:52Z","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/1908.05758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent progress in machine learning, boosted by techniques such as deep learning, many tasks can be successfully solved once a large enough dataset is available for training. Nonetheless, human-annotated datasets are often expensive to produce, especially when labels are fine-grained, as is the case of Named Entity Recognition (NER), a task that operates with labels on a word-level.\n  In this paper, we propose a method to automatically generate labeled datasets for NER from public data sources by exploiting links and structured data from DBpedia and Wikipedia. Due to the massive size ","authors_text":"Daniel Specht Menezes, Pedro Savarese, Ruy Luiz Milidi\\'u","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T03:47:03Z","title":"Building a Massive Corpus for Named Entity Recognition using Free Open Data Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05758","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":"sha256:0065b807ab8dec1f0d8ac65e38b78a5ed21e4c5eeb9d139551d1f2f6609c0411","target":"record","created_at":"2026-07-04T23:57:52Z","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":"52a0c3d32611c9bd0b71a5a22ea2ab6c159cd968810fff06daf22745064f0f94","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-13T03:47:03Z","title_canon_sha256":"1405d5cbfff695e1f41d0655fe9707db92fb36ed14159fa15b1f0eab668d91a2"},"schema_version":"1.0","source":{"id":"1908.05758","kind":"arxiv","version":1}},"canonical_sha256":"6344feb527faa56fdb9e41dbfbf65754d4321e42d9945693d629e613861a87d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6344feb527faa56fdb9e41dbfbf65754d4321e42d9945693d629e613861a87d6","first_computed_at":"2026-07-04T23:57:52.928427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:57:52.928427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4/tiv4YqAFo4E0AUUVH24KGr3Tr9mmuN2P6hEtHyQR8LLI2tPFeWVDcF93SuUge3kgXxtJ/Jq0TJP6/o12vhCw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:57:52.928837Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05758","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0065b807ab8dec1f0d8ac65e38b78a5ed21e4c5eeb9d139551d1f2f6609c0411","sha256:15b91484e576ef15e71069e511a06f0db39b1391a33083376c775d2a7b60216b"],"state_sha256":"2fff2c5c0561e59d9fccd3998bc87b08a2654a67d9cbc85a2d016c2bac733ca1"}