{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3PDBQCOG4BSR3BEEFEC2QZQCAC","short_pith_number":"pith:3PDBQCOG","canonical_record":{"source":{"id":"1809.00732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T21:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"7480a5ac1e5aeae50e82bf773e938b5b763d4d7c2b38534a303c88c99df15ac5","abstract_canon_sha256":"b0839efd7833833a831a7eb8d6d94512d74b0da29c3e889fcd294a9127692869"},"schema_version":"1.0"},"canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","source":{"kind":"arxiv","id":"1809.00732","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00732","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00732v1","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00732","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"3PDBQCOG4BSR","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3PDBQCOG4BSR3BEE","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3PDBQCOG","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3PDBQCOG4BSR3BEEFEC2QZQCAC","target":"record","payload":{"canonical_record":{"source":{"id":"1809.00732","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T21:56:47Z","cross_cats_sorted":[],"title_canon_sha256":"7480a5ac1e5aeae50e82bf773e938b5b763d4d7c2b38534a303c88c99df15ac5","abstract_canon_sha256":"b0839efd7833833a831a7eb8d6d94512d74b0da29c3e889fcd294a9127692869"},"schema_version":"1.0"},"canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:32.629375Z","signature_b64":"WR3rr+0mYr9PQqHac+7qaNxSYhL+NfTnyq2izhSBBP8IvTDN+mWEBUwmt9eF7JcbNmEKUuDFyTL6kS2LoUWuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","last_reissued_at":"2026-05-18T00:06:32.628892Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:32.628892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.00732","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8tOjLnIle9640VQvpbK9iPlhOQe+zaZCUg1TWQR4gDyxxarU7kMgSm+TcYyu4NtGEbVrGO7bBZfAZtDACKpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T21:55:31.232710Z"},"content_sha256":"43bc94c16406f75041334dd68df85140f918131d1d718574be645170bb006ff5","schema_version":"1.0","event_id":"sha256:43bc94c16406f75041334dd68df85140f918131d1d718574be645170bb006ff5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3PDBQCOG4BSR3BEEFEC2QZQCAC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anusri Pampari, Jennifer Liang, Jian Peng, Preethi Raghavan","submitted_at":"2018-09-03T21:56:47Z","abstract_excerpt":"We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million question-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00732","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2sZRi/zICgtzW1m8ZUCgaO6W5Zg27++9Cx3emrkiw9kKDmoS2R/hbNvEzbkY71EgmcPRSwbQ6Q2pVruNIB5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T21:55:31.233353Z"},"content_sha256":"d7f1fe1fa413ea7e8c1684cdc7e29f89c9db9fadb5ba1e81787d2504d6e958c3","schema_version":"1.0","event_id":"sha256:d7f1fe1fa413ea7e8c1684cdc7e29f89c9db9fadb5ba1e81787d2504d6e958c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/bundle.json","state_url":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T21:55:31Z","links":{"resolver":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC","bundle":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/bundle.json","state":"https://pith.science/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3PDBQCOG4BSR3BEEFEC2QZQCAC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3PDBQCOG4BSR3BEEFEC2QZQCAC","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":"b0839efd7833833a831a7eb8d6d94512d74b0da29c3e889fcd294a9127692869","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T21:56:47Z","title_canon_sha256":"7480a5ac1e5aeae50e82bf773e938b5b763d4d7c2b38534a303c88c99df15ac5"},"schema_version":"1.0","source":{"id":"1809.00732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.00732","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"arxiv_version","alias_value":"1809.00732v1","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.00732","created_at":"2026-05-18T00:06:32Z"},{"alias_kind":"pith_short_12","alias_value":"3PDBQCOG4BSR","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"3PDBQCOG4BSR3BEE","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"3PDBQCOG","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:d7f1fe1fa413ea7e8c1684cdc7e29f89c9db9fadb5ba1e81787d2504d6e958c3","target":"graph","created_at":"2026-05-18T00:06:32Z","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"},"paper":{"abstract_excerpt":"We propose a novel methodology to generate domain-specific large-scale question answering (QA) datasets by re-purposing existing annotations for other NLP tasks. We demonstrate an instance of this methodology in generating a large-scale QA dataset for electronic medical records by leveraging existing expert annotations on clinical notes for various NLP tasks from the community shared i2b2 datasets. The resulting corpus (emrQA) has 1 million question-logical form and 400,000+ question-answer evidence pairs. We characterize the dataset and explore its learning potential by training baseline mode","authors_text":"Anusri Pampari, Jennifer Liang, Jian Peng, Preethi Raghavan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T21:56:47Z","title":"emrQA: A Large Corpus for Question Answering on Electronic Medical Records"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.00732","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":"sha256:43bc94c16406f75041334dd68df85140f918131d1d718574be645170bb006ff5","target":"record","created_at":"2026-05-18T00:06:32Z","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":"b0839efd7833833a831a7eb8d6d94512d74b0da29c3e889fcd294a9127692869","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-03T21:56:47Z","title_canon_sha256":"7480a5ac1e5aeae50e82bf773e938b5b763d4d7c2b38534a303c88c99df15ac5"},"schema_version":"1.0","source":{"id":"1809.00732","kind":"arxiv","version":1}},"canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbc61809c6e0651d84842905a866020094080759853916233b772761f5cd211d","first_computed_at":"2026-05-18T00:06:32.628892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:32.628892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WR3rr+0mYr9PQqHac+7qaNxSYhL+NfTnyq2izhSBBP8IvTDN+mWEBUwmt9eF7JcbNmEKUuDFyTL6kS2LoUWuDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:32.629375Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.00732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43bc94c16406f75041334dd68df85140f918131d1d718574be645170bb006ff5","sha256:d7f1fe1fa413ea7e8c1684cdc7e29f89c9db9fadb5ba1e81787d2504d6e958c3"],"state_sha256":"4fa5b6678f32e8cdb9b9633c5c4595a543bca22fc738288f83830a1ddaa00d65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQK5hDtZAwA81pqe4nFHkoFPBUD2hO69dbEHs5Hy6UPYwYXn2xRZ9egfgtrNLmYHzqZ8Uf8PxwsVW7qtwqX7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T21:55:31.237113Z","bundle_sha256":"cdc199439f5307de3d8bf926ce7686bbaa1a2446e1133cedcc53dc4a7067bd40"}}