{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5A5C4IFX6634R4LGQQA4V35HVN","short_pith_number":"pith:5A5C4IFX","canonical_record":{"source":{"id":"1908.08419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:51:44Z","cross_cats_sorted":[],"title_canon_sha256":"bd41523251b2ae2220a27b48867e69e4db4d20cefe234791c8e9bb5f487e7090","abstract_canon_sha256":"f38e142f6bb8ef5118c89dcd7977af870fb1411fb66abbded34bb5dde70d0ffa"},"schema_version":"1.0"},"canonical_sha256":"e83a2e20b7f7b7c8f1668401caefa7ab5335971fc8d0b1362b16a4975525cdb6","source":{"kind":"arxiv","id":"1908.08419","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08419","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08419v3","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08419","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"5A5C4IFX6634","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"5A5C4IFX6634R4LG","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"5A5C4IFX","created_at":"2026-07-05T01:19:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5A5C4IFX6634R4LGQQA4V35HVN","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:51:44Z","cross_cats_sorted":[],"title_canon_sha256":"bd41523251b2ae2220a27b48867e69e4db4d20cefe234791c8e9bb5f487e7090","abstract_canon_sha256":"f38e142f6bb8ef5118c89dcd7977af870fb1411fb66abbded34bb5dde70d0ffa"},"schema_version":"1.0"},"canonical_sha256":"e83a2e20b7f7b7c8f1668401caefa7ab5335971fc8d0b1362b16a4975525cdb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:50.215904Z","signature_b64":"bKuKNXqo/NwIknvyxECBC/vrVyz/sxKI9MsXe1BgBwQ1cCC2Rr0kWeepQCt2R09Zw4CNOInMvwl7mA/OoDDXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83a2e20b7f7b7c8f1668401caefa7ab5335971fc8d0b1362b16a4975525cdb6","last_reissued_at":"2026-07-05T01:19:50.215410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:50.215410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08419","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBPPc1gj8KNvKFvXbhGNUDeoPM0TRBIXYM0pMw+UHXLn3IfcRI3wty8/l+UVu2SMV+6/gyhtMuzdiaxwjuLWAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:59:45.823184Z"},"content_sha256":"71fbfb60458b84d889118946cbec99de223da0fae6b45027ab76622ef72a2c92","schema_version":"1.0","event_id":"sha256:71fbfb60458b84d889118946cbec99de223da0fae6b45027ab76622ef72a2c92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5A5C4IFX6634R4LGQQA4V35HVN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Zheng, Tingting Cai, Yangming Zhou, Zhiyuan Ma","submitted_at":"2019-08-22T14:51:44Z","abstract_excerpt":"Electronic Health Records (EHRs) in hospital information systems contain patients' diagnosis and treatments, so EHRs are essential to clinical data mining. Of all the tasks in the mining process, Chinese Word Segmentation (CWS) is a fundamental and important one, and most state-of-the-art methods greatly rely on large-scale of manually-annotated data. Since annotation is time-consuming and expensive, efforts have been devoted to techniques, such as active learning, to locate the most informative samples for modeling. In this paper, we follow the trend and present an active learning method for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08419","kind":"arxiv","version":3},"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/1908.08419/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:19:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7Z9avvAuGvHvqZxx40HCPKlIZ6Fo8YS4/kAEK49yMiyazkhA+Ytzpblawe8hwDG5KXWkbry5y52IZVQepP3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T10:59:45.824170Z"},"content_sha256":"7f8b06775c03ceed056d875136215756877f7508f8c8d1ecf47f4d650bde44b4","schema_version":"1.0","event_id":"sha256:7f8b06775c03ceed056d875136215756877f7508f8c8d1ecf47f4d650bde44b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5A5C4IFX6634R4LGQQA4V35HVN/bundle.json","state_url":"https://pith.science/pith/5A5C4IFX6634R4LGQQA4V35HVN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5A5C4IFX6634R4LGQQA4V35HVN/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":"2026-08-16T10:59:45Z","links":{"resolver":"https://pith.science/pith/5A5C4IFX6634R4LGQQA4V35HVN","bundle":"https://pith.science/pith/5A5C4IFX6634R4LGQQA4V35HVN/bundle.json","state":"https://pith.science/pith/5A5C4IFX6634R4LGQQA4V35HVN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5A5C4IFX6634R4LGQQA4V35HVN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5A5C4IFX6634R4LGQQA4V35HVN","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":"f38e142f6bb8ef5118c89dcd7977af870fb1411fb66abbded34bb5dde70d0ffa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:51:44Z","title_canon_sha256":"bd41523251b2ae2220a27b48867e69e4db4d20cefe234791c8e9bb5f487e7090"},"schema_version":"1.0","source":{"id":"1908.08419","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08419","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08419v3","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08419","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"pith_short_12","alias_value":"5A5C4IFX6634","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"pith_short_16","alias_value":"5A5C4IFX6634R4LG","created_at":"2026-07-05T01:19:50Z"},{"alias_kind":"pith_short_8","alias_value":"5A5C4IFX","created_at":"2026-07-05T01:19:50Z"}],"graph_snapshots":[{"event_id":"sha256:7f8b06775c03ceed056d875136215756877f7508f8c8d1ecf47f4d650bde44b4","target":"graph","created_at":"2026-07-05T01:19:50Z","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/1908.08419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Electronic Health Records (EHRs) in hospital information systems contain patients' diagnosis and treatments, so EHRs are essential to clinical data mining. Of all the tasks in the mining process, Chinese Word Segmentation (CWS) is a fundamental and important one, and most state-of-the-art methods greatly rely on large-scale of manually-annotated data. Since annotation is time-consuming and expensive, efforts have been devoted to techniques, such as active learning, to locate the most informative samples for modeling. In this paper, we follow the trend and present an active learning method for ","authors_text":"Hong Zheng, Tingting Cai, Yangming Zhou, Zhiyuan Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:51:44Z","title":"NE-LP: Normalized Entropy and Loss Prediction based Sampling for Active Learning in Chinese Word Segmentation on EHRs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08419","kind":"arxiv","version":3},"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":"sha256:71fbfb60458b84d889118946cbec99de223da0fae6b45027ab76622ef72a2c92","target":"record","created_at":"2026-07-05T01:19:50Z","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":"f38e142f6bb8ef5118c89dcd7977af870fb1411fb66abbded34bb5dde70d0ffa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:51:44Z","title_canon_sha256":"bd41523251b2ae2220a27b48867e69e4db4d20cefe234791c8e9bb5f487e7090"},"schema_version":"1.0","source":{"id":"1908.08419","kind":"arxiv","version":3}},"canonical_sha256":"e83a2e20b7f7b7c8f1668401caefa7ab5335971fc8d0b1362b16a4975525cdb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e83a2e20b7f7b7c8f1668401caefa7ab5335971fc8d0b1362b16a4975525cdb6","first_computed_at":"2026-07-05T01:19:50.215410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:19:50.215410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bKuKNXqo/NwIknvyxECBC/vrVyz/sxKI9MsXe1BgBwQ1cCC2Rr0kWeepQCt2R09Zw4CNOInMvwl7mA/OoDDXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:19:50.215904Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08419","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71fbfb60458b84d889118946cbec99de223da0fae6b45027ab76622ef72a2c92","sha256:7f8b06775c03ceed056d875136215756877f7508f8c8d1ecf47f4d650bde44b4"],"state_sha256":"3e6de13c88ada47a6c49d4f9b2961d6da053501f24ec5d72c825cd00d0cf2c3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQzVJwMzLL60Yom2LbmpthGPw6aAiea9AKH/ViyhQiJMVBu7wXpU13o2HJGDkp2ulvM+wCuJdIcaiVCpp+gpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T10:59:45.830701Z","bundle_sha256":"4adfb500d9afc64f1d7b8962576b50e62dc943b9c41dc9a9e1925b30bb845d32"}}