{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CPY3HDPBBCDVBZNPZVIPARFUGT","short_pith_number":"pith:CPY3HDPB","schema_version":"1.0","canonical_sha256":"13f1b38de1088750e5afcd50f044b434da57423ad6cdfa2c07f0ad2f8d824da2","source":{"kind":"arxiv","id":"1911.10436","version":1},"attestation_state":"computed","paper":{"title":"ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannah Smith, John Culnan, Peter Jansen, Zeyu Zhang","submitted_at":"2019-11-24T00:08:09Z","abstract_excerpt":"Named entity recognition identifies common classes of entities in text, but these entity labels are generally sparse, limiting utility to downstream tasks. In this work we present ScienceExamCER, a densely-labeled semantic classification corpus of 133k mentions in the science exam domain where nearly all (96%) of content words have been annotated with one or more fine-grained semantic class labels including taxonomic groups, meronym groups, verb/action groups, properties and values, and synonyms. Semantic class labels are drawn from a manually-constructed fine-grained typology of 601 classes g"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.10436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-24T00:08:09Z","cross_cats_sorted":[],"title_canon_sha256":"17f5e753229d0a4dd8336ee6b2866f3f050dbd12e4ad78a05ea289a5ed489bd1","abstract_canon_sha256":"949de28b732a04df495eac1dffe69e4410b0e4fc4af294701bdadebdac25a9b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:40.191803Z","signature_b64":"23QLrUs9qmW25I9a5sOXQ6To4ag4Kb5ESmJjyIcRLYQCovCm3zoIBq1ZwKAVfIlkmyFOKxBKVzJ/VcKQQY83Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13f1b38de1088750e5afcd50f044b434da57423ad6cdfa2c07f0ad2f8d824da2","last_reissued_at":"2026-07-05T00:21:40.191333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:40.191333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScienceExamCER: A High-Density Fine-Grained Science-Domain Corpus for Common Entity Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hannah Smith, John Culnan, Peter Jansen, Zeyu Zhang","submitted_at":"2019-11-24T00:08:09Z","abstract_excerpt":"Named entity recognition identifies common classes of entities in text, but these entity labels are generally sparse, limiting utility to downstream tasks. In this work we present ScienceExamCER, a densely-labeled semantic classification corpus of 133k mentions in the science exam domain where nearly all (96%) of content words have been annotated with one or more fine-grained semantic class labels including taxonomic groups, meronym groups, verb/action groups, properties and values, and synonyms. Semantic class labels are drawn from a manually-constructed fine-grained typology of 601 classes g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.10436","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.10436/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.10436","created_at":"2026-07-05T00:21:40.191387+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.10436v1","created_at":"2026-07-05T00:21:40.191387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.10436","created_at":"2026-07-05T00:21:40.191387+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPY3HDPBBCDV","created_at":"2026-07-05T00:21:40.191387+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPY3HDPBBCDVBZNP","created_at":"2026-07-05T00:21:40.191387+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPY3HDPB","created_at":"2026-07-05T00:21:40.191387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT","json":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT.json","graph_json":"https://pith.science/api/pith-number/CPY3HDPBBCDVBZNPZVIPARFUGT/graph.json","events_json":"https://pith.science/api/pith-number/CPY3HDPBBCDVBZNPZVIPARFUGT/events.json","paper":"https://pith.science/paper/CPY3HDPB"},"agent_actions":{"view_html":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT","download_json":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT.json","view_paper":"https://pith.science/paper/CPY3HDPB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.10436&json=true","fetch_graph":"https://pith.science/api/pith-number/CPY3HDPBBCDVBZNPZVIPARFUGT/graph.json","fetch_events":"https://pith.science/api/pith-number/CPY3HDPBBCDVBZNPZVIPARFUGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT/action/storage_attestation","attest_author":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT/action/author_attestation","sign_citation":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT/action/citation_signature","submit_replication":"https://pith.science/pith/CPY3HDPBBCDVBZNPZVIPARFUGT/action/replication_record"}},"created_at":"2026-07-05T00:21:40.191387+00:00","updated_at":"2026-07-05T00:21:40.191387+00:00"}