{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RPIJFXC5AN7ID5YERQMOER2SAI","short_pith_number":"pith:RPIJFXC5","canonical_record":{"source":{"id":"1804.07814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-20T20:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"9935ee9ae9ca4a930a730b20e653005d3a45b416cb04aaf3ae23a6e77c74c4ce","abstract_canon_sha256":"37ea191f18fd6dfbbc936733fdf346b516e79bfcaf6cff54ab9ea84660a99cfd"},"schema_version":"1.0"},"canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","source":{"kind":"arxiv","id":"1804.07814","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07814","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07814v1","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07814","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"RPIJFXC5AN7I","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RPIJFXC5AN7ID5YE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RPIJFXC5","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RPIJFXC5AN7ID5YERQMOER2SAI","target":"record","payload":{"canonical_record":{"source":{"id":"1804.07814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-20T20:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"9935ee9ae9ca4a930a730b20e653005d3a45b416cb04aaf3ae23a6e77c74c4ce","abstract_canon_sha256":"37ea191f18fd6dfbbc936733fdf346b516e79bfcaf6cff54ab9ea84660a99cfd"},"schema_version":"1.0"},"canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:52.682338Z","signature_b64":"E7EPX3EcRewJumikr+a9pYY/xJN6p1IV0+iKK78HVpeubOno4fBxuo3Kyn21/nwT5TdtJelzdYOaT3NtWUwoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","last_reissued_at":"2026-05-18T00:17:52.681725Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:52.681725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.07814","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":"2026-05-18T00:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e5UYQ6FnzHXIchB9+wPdCFw+6hY63gAqwp6wZuRICEyk7Xz9W19vmtz5UCSPmaUsuE1SdsP5A4Vf0PgY7EoaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:18:35.153943Z"},"content_sha256":"d6fb7f64c3b25d3fd7aebf4400dda3a6e3e5629ecb88d9e3bd38b3990b1a451e","schema_version":"1.0","event_id":"sha256:d6fb7f64c3b25d3fd7aebf4400dda3a6e3e5629ecb88d9e3bd38b3990b1a451e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RPIJFXC5AN7ID5YERQMOER2SAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Deep Representation Empowered Distant Supervision Paradigm for Clinical Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Elizabeth J. Atkinson, Feichen Shen, Hongfang Liu, Liwei Wang, Shreyasee Amin, Sijia Liu, Sunghwan Sohn, Yanshan Wang","submitted_at":"2018-04-20T20:18:46Z","abstract_excerpt":"Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant supervision paradigm empowered by deep representation for extracting information from clinical text. In this paradigm, the rule-based NLP algorithms are utilized to generate weak labels and create large training datasets automatically. Additionally, we use pre-trained word embeddings as deep representation to eliminate the need of task-specific feature engin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07814","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":"2026-05-18T00:17:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOCEKPHMI1YVzkobHtvrDKpLvcDZ4BhMQUoXzfIVaryAPVt1qnDQ0MlZDRedMpCvN6ElonLBSLZAnG4+jc3xAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:18:35.154651Z"},"content_sha256":"367d010e130f66fd56b073d978055c7c707978a4b9f0a44d837e7b36eaca9521","schema_version":"1.0","event_id":"sha256:367d010e130f66fd56b073d978055c7c707978a4b9f0a44d837e7b36eaca9521"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/bundle.json","state_url":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RPIJFXC5AN7ID5YERQMOER2SAI/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":"2026-05-27T11:18:35Z","links":{"resolver":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI","bundle":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/bundle.json","state":"https://pith.science/pith/RPIJFXC5AN7ID5YERQMOER2SAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RPIJFXC5AN7ID5YERQMOER2SAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RPIJFXC5AN7ID5YERQMOER2SAI","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":"37ea191f18fd6dfbbc936733fdf346b516e79bfcaf6cff54ab9ea84660a99cfd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-20T20:18:46Z","title_canon_sha256":"9935ee9ae9ca4a930a730b20e653005d3a45b416cb04aaf3ae23a6e77c74c4ce"},"schema_version":"1.0","source":{"id":"1804.07814","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.07814","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"arxiv_version","alias_value":"1804.07814v1","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07814","created_at":"2026-05-18T00:17:52Z"},{"alias_kind":"pith_short_12","alias_value":"RPIJFXC5AN7I","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RPIJFXC5AN7ID5YE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RPIJFXC5","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:367d010e130f66fd56b073d978055c7c707978a4b9f0a44d837e7b36eaca9521","target":"graph","created_at":"2026-05-18T00:17:52Z","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"},"paper":{"abstract_excerpt":"Objective: To automatically create large labeled training datasets and reduce the efforts of feature engineering for training accurate machine learning models for clinical information extraction. Materials and Methods: We propose a distant supervision paradigm empowered by deep representation for extracting information from clinical text. In this paradigm, the rule-based NLP algorithms are utilized to generate weak labels and create large training datasets automatically. Additionally, we use pre-trained word embeddings as deep representation to eliminate the need of task-specific feature engin","authors_text":"Elizabeth J. Atkinson, Feichen Shen, Hongfang Liu, Liwei Wang, Shreyasee Amin, Sijia Liu, Sunghwan Sohn, Yanshan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-20T20:18:46Z","title":"A Deep Representation Empowered Distant Supervision Paradigm for Clinical Information Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07814","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:d6fb7f64c3b25d3fd7aebf4400dda3a6e3e5629ecb88d9e3bd38b3990b1a451e","target":"record","created_at":"2026-05-18T00:17:52Z","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":"37ea191f18fd6dfbbc936733fdf346b516e79bfcaf6cff54ab9ea84660a99cfd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-04-20T20:18:46Z","title_canon_sha256":"9935ee9ae9ca4a930a730b20e653005d3a45b416cb04aaf3ae23a6e77c74c4ce"},"schema_version":"1.0","source":{"id":"1804.07814","kind":"arxiv","version":1}},"canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bd092dc5d037e81f7048c18e24752022a0b095865a34672808cf4e7e6788ef9","first_computed_at":"2026-05-18T00:17:52.681725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:52.681725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E7EPX3EcRewJumikr+a9pYY/xJN6p1IV0+iKK78HVpeubOno4fBxuo3Kyn21/nwT5TdtJelzdYOaT3NtWUwoDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:52.682338Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.07814","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6fb7f64c3b25d3fd7aebf4400dda3a6e3e5629ecb88d9e3bd38b3990b1a451e","sha256:367d010e130f66fd56b073d978055c7c707978a4b9f0a44d837e7b36eaca9521"],"state_sha256":"70ef83fb163bf5829de646152a246706fbba7e52f456f17978992f03f2c3bfdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBPeApqiHuUQiPvBUKf4dgpgwir6Zg1BBFNLgkwxpgk7F2BwoGtMHN8ngmgxuCrgM2EyVfflA/TXrCSKQ+fmCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:18:35.158225Z","bundle_sha256":"cb1affc93a11f4367abed2551e38dfcd1372b98bdea6ece44ffe9de6c002d509"}}