{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LTBFC6LEZ5NK7QWDBLQIMQGBTY","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":"9ecd74a7ee7e13a32e5eb212e94b7a20984ec774d3e19ff4b4fb50b5f9c5b4e5","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T17:30:10Z","title_canon_sha256":"dcbcb15480e7990e60fac63751364ad34d47f15c86c33f4aa41e3ed61d4fe779"},"schema_version":"1.0","source":{"id":"2005.00512","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00512","created_at":"2026-07-05T00:59:41Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00512v1","created_at":"2026-07-05T00:59:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00512","created_at":"2026-07-05T00:59:41Z"},{"alias_kind":"pith_short_12","alias_value":"LTBFC6LEZ5NK","created_at":"2026-07-05T00:59:41Z"},{"alias_kind":"pith_short_16","alias_value":"LTBFC6LEZ5NK7QWD","created_at":"2026-07-05T00:59:41Z"},{"alias_kind":"pith_short_8","alias_value":"LTBFC6LE","created_at":"2026-07-05T00:59:41Z"}],"graph_snapshots":[{"event_id":"sha256:a8d4349cc348932c3cb2ea27f0eb97fb6c3a65a4bbb027c936ad2e9785022d80","target":"graph","created_at":"2026-07-05T00:59:41Z","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/2005.00512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting information from full documents is an important problem in many domains, but most previous work focus on identifying relationships within a sentence or a paragraph. It is challenging to create a large-scale information extraction (IE) dataset at the document level since it requires an understanding of the whole document to annotate entities and their document-level relationships that usually span beyond sentences or even sections. In this paper, we introduce SciREX, a document level IE dataset that encompasses multiple IE tasks, including salient entity identification and document l","authors_text":"Hannaneh Hajishirzi, Iz Beltagy, Madeleine van Zuylen, Sarthak Jain","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T17:30:10Z","title":"SciREX: A Challenge Dataset for Document-Level Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00512","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":"sha256:50795d1c119ff3bb3c1f63c507846a597d5a37af93c54f88661b8efcfdcb8b86","target":"record","created_at":"2026-07-05T00:59:41Z","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":"9ecd74a7ee7e13a32e5eb212e94b7a20984ec774d3e19ff4b4fb50b5f9c5b4e5","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T17:30:10Z","title_canon_sha256":"dcbcb15480e7990e60fac63751364ad34d47f15c86c33f4aa41e3ed61d4fe779"},"schema_version":"1.0","source":{"id":"2005.00512","kind":"arxiv","version":1}},"canonical_sha256":"5cc2517964cf5aafc2c30ae08640c19e2e6dbc7151c9eb250e75a36a1cd9f54c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cc2517964cf5aafc2c30ae08640c19e2e6dbc7151c9eb250e75a36a1cd9f54c","first_computed_at":"2026-07-05T00:59:41.576082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:41.576082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sgl3iamOrIlKF/vogSmEIwlj/hNmhFUy887P0klilVT+cycNT4Im4mD6Ws//t22Zxskr5mGPxyBSd34Hla5sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:41.576524Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00512","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50795d1c119ff3bb3c1f63c507846a597d5a37af93c54f88661b8efcfdcb8b86","sha256:a8d4349cc348932c3cb2ea27f0eb97fb6c3a65a4bbb027c936ad2e9785022d80"],"state_sha256":"f56175deb7c1109fd6e37127d407e4e2fe3f0dec12ce4923a4e1097d050eb98a"}