{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BV3YYVWRP3MDIM3PGG5RE7SFJN","short_pith_number":"pith:BV3YYVWR","schema_version":"1.0","canonical_sha256":"0d778c56d17ed834336f31bb127e454b654ce063ada1ef96d1504b02b55ec82e","source":{"kind":"arxiv","id":"2101.11177","version":1},"attestation_state":"computed","paper":{"title":"LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jacob Solawetz, Stefan Larson","submitted_at":"2021-01-27T02:49:26Z","abstract_excerpt":"Open Information Extraction (OIE) systems seek to compress the factual propositions of a sentence into a series of n-ary tuples. These tuples are useful for downstream tasks in natural language processing like knowledge base creation, textual entailment, and natural language understanding. However, current OIE datasets are limited in both size and diversity. We introduce a new dataset by converting the QA-SRL 2.0 dataset to a large-scale OIE dataset (LSOIE). Our LSOIE dataset is 20 times larger than the next largest human-annotated OIE dataset. We construct and evaluate several benchmark OIE m"},"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":"2101.11177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-27T02:49:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f37aec565508e220b1cd54897a728d13c4a2cc28ebd1a30e27efc17584078e3d","abstract_canon_sha256":"234bff31214dcbe2a061b261b59f62171b8bb4d9971f51e410a23a2ef9648bd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:09.925033Z","signature_b64":"tlCjDMdFc5//l+K+fO0J7lhqWVacIe603TqK07GxmDI/AUaHjKYbIXgUTTTdkJuYFQH7RqobCF0YprzRwZWKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d778c56d17ed834336f31bb127e454b654ce063ada1ef96d1504b02b55ec82e","last_reissued_at":"2026-07-05T02:10:09.924624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:09.924624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSOIE: A Large-Scale Dataset for Supervised Open Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jacob Solawetz, Stefan Larson","submitted_at":"2021-01-27T02:49:26Z","abstract_excerpt":"Open Information Extraction (OIE) systems seek to compress the factual propositions of a sentence into a series of n-ary tuples. These tuples are useful for downstream tasks in natural language processing like knowledge base creation, textual entailment, and natural language understanding. However, current OIE datasets are limited in both size and diversity. We introduce a new dataset by converting the QA-SRL 2.0 dataset to a large-scale OIE dataset (LSOIE). Our LSOIE dataset is 20 times larger than the next largest human-annotated OIE dataset. We construct and evaluate several benchmark OIE m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.11177","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/2101.11177/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":"2101.11177","created_at":"2026-07-05T02:10:09.924680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.11177v1","created_at":"2026-07-05T02:10:09.924680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.11177","created_at":"2026-07-05T02:10:09.924680+00:00"},{"alias_kind":"pith_short_12","alias_value":"BV3YYVWRP3MD","created_at":"2026-07-05T02:10:09.924680+00:00"},{"alias_kind":"pith_short_16","alias_value":"BV3YYVWRP3MDIM3P","created_at":"2026-07-05T02:10:09.924680+00:00"},{"alias_kind":"pith_short_8","alias_value":"BV3YYVWR","created_at":"2026-07-05T02:10:09.924680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17187","citing_title":"PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media","ref_index":277,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN","json":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN.json","graph_json":"https://pith.science/api/pith-number/BV3YYVWRP3MDIM3PGG5RE7SFJN/graph.json","events_json":"https://pith.science/api/pith-number/BV3YYVWRP3MDIM3PGG5RE7SFJN/events.json","paper":"https://pith.science/paper/BV3YYVWR"},"agent_actions":{"view_html":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN","download_json":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN.json","view_paper":"https://pith.science/paper/BV3YYVWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.11177&json=true","fetch_graph":"https://pith.science/api/pith-number/BV3YYVWRP3MDIM3PGG5RE7SFJN/graph.json","fetch_events":"https://pith.science/api/pith-number/BV3YYVWRP3MDIM3PGG5RE7SFJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN/action/storage_attestation","attest_author":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN/action/author_attestation","sign_citation":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN/action/citation_signature","submit_replication":"https://pith.science/pith/BV3YYVWRP3MDIM3PGG5RE7SFJN/action/replication_record"}},"created_at":"2026-07-05T02:10:09.924680+00:00","updated_at":"2026-07-05T02:10:09.924680+00:00"}