{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ASIKRO2DOP7WJB3JQYOXDUW633","short_pith_number":"pith:ASIKRO2D","canonical_record":{"source":{"id":"2108.09913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T03:48:27Z","cross_cats_sorted":[],"title_canon_sha256":"dad66ada63075029866cb897d7c47cf385fab47dead7e90c201b9f39fbc3bd56","abstract_canon_sha256":"c6dd74ab01274ff1dbc45f09211c65d2b4761ff761fa6b33893e7030dee58089"},"schema_version":"1.0"},"canonical_sha256":"0490a8bb4373ff648769861d71d2dedef2d765a4ceccf81726fa87a0425166e3","source":{"kind":"arxiv","id":"2108.09913","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09913","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09913v1","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09913","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_12","alias_value":"ASIKRO2DOP7W","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_16","alias_value":"ASIKRO2DOP7WJB3J","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_8","alias_value":"ASIKRO2D","created_at":"2026-07-05T03:07:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ASIKRO2DOP7WJB3JQYOXDUW633","target":"record","payload":{"canonical_record":{"source":{"id":"2108.09913","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T03:48:27Z","cross_cats_sorted":[],"title_canon_sha256":"dad66ada63075029866cb897d7c47cf385fab47dead7e90c201b9f39fbc3bd56","abstract_canon_sha256":"c6dd74ab01274ff1dbc45f09211c65d2b4761ff761fa6b33893e7030dee58089"},"schema_version":"1.0"},"canonical_sha256":"0490a8bb4373ff648769861d71d2dedef2d765a4ceccf81726fa87a0425166e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:59.820272Z","signature_b64":"AbaeRcPgzv02x/PouKR8x2NoWH5EVtWI3qGW8Q4GBrf5pHEYRazL5MR10HOmgGs0o7oYxveMfzBhwpk8WX7SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0490a8bb4373ff648769861d71d2dedef2d765a4ceccf81726fa87a0425166e3","last_reissued_at":"2026-07-05T03:07:59.819872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:59.819872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.09913","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":"2026-07-05T03:07:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03mvvrXEiEgC4CxGy7dbq6TJEFemH4FNzTJsQEnCsep7HIHj2jkmBcKgXfpfSaVSpx2hPTBsLJ3MtldUDlwsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:12:56.102601Z"},"content_sha256":"16c96b14f0cd5dfe102d78c7cc9a27ca26db8972b4df12a699ce5d854149d53c","schema_version":"1.0","event_id":"sha256:16c96b14f0cd5dfe102d78c7cc9a27ca26db8972b4df12a699ce5d854149d53c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ASIKRO2DOP7WJB3JQYOXDUW633","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analyzing the Granularity and Cost of Annotation in Clinical Sequence Labeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenchen Xu, Hanna Suominen, Haozhan Sun","submitted_at":"2021-08-23T03:48:27Z","abstract_excerpt":"Well-annotated datasets, as shown in recent top studies, are becoming more important for researchers than ever before in supervised machine learning (ML). However, the dataset annotation process and its related human labor costs remain overlooked. In this work, we analyze the relationship between the annotation granularity and ML performance in sequence labeling, using clinical records from nursing shift-change handover. We first study a model derived from textual language features alone, without additional information based on nursing knowledge. We find that this sequence tagger performs well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09913","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/2108.09913/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":"2026-07-05T03:07:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Ju4+MZPerRxUHyNFrS1scjHRG66fraOAY5vjO07wElqx7Eo/dvzUfWzf00XiXPT4382PhATgMWnPpJY8nhnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:12:56.103123Z"},"content_sha256":"86075bc69d3a62428497ca547f3e36e8cb58ce71cdecd0946f293012327565f8","schema_version":"1.0","event_id":"sha256:86075bc69d3a62428497ca547f3e36e8cb58ce71cdecd0946f293012327565f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASIKRO2DOP7WJB3JQYOXDUW633/bundle.json","state_url":"https://pith.science/pith/ASIKRO2DOP7WJB3JQYOXDUW633/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASIKRO2DOP7WJB3JQYOXDUW633/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":"2026-08-22T23:12:56Z","links":{"resolver":"https://pith.science/pith/ASIKRO2DOP7WJB3JQYOXDUW633","bundle":"https://pith.science/pith/ASIKRO2DOP7WJB3JQYOXDUW633/bundle.json","state":"https://pith.science/pith/ASIKRO2DOP7WJB3JQYOXDUW633/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASIKRO2DOP7WJB3JQYOXDUW633/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ASIKRO2DOP7WJB3JQYOXDUW633","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":"c6dd74ab01274ff1dbc45f09211c65d2b4761ff761fa6b33893e7030dee58089","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T03:48:27Z","title_canon_sha256":"dad66ada63075029866cb897d7c47cf385fab47dead7e90c201b9f39fbc3bd56"},"schema_version":"1.0","source":{"id":"2108.09913","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09913","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09913v1","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09913","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_12","alias_value":"ASIKRO2DOP7W","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_16","alias_value":"ASIKRO2DOP7WJB3J","created_at":"2026-07-05T03:07:59Z"},{"alias_kind":"pith_short_8","alias_value":"ASIKRO2D","created_at":"2026-07-05T03:07:59Z"}],"graph_snapshots":[{"event_id":"sha256:86075bc69d3a62428497ca547f3e36e8cb58ce71cdecd0946f293012327565f8","target":"graph","created_at":"2026-07-05T03:07:59Z","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/2108.09913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Well-annotated datasets, as shown in recent top studies, are becoming more important for researchers than ever before in supervised machine learning (ML). However, the dataset annotation process and its related human labor costs remain overlooked. In this work, we analyze the relationship between the annotation granularity and ML performance in sequence labeling, using clinical records from nursing shift-change handover. We first study a model derived from textual language features alone, without additional information based on nursing knowledge. We find that this sequence tagger performs well","authors_text":"Chenchen Xu, Hanna Suominen, Haozhan Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T03:48:27Z","title":"Analyzing the Granularity and Cost of Annotation in Clinical Sequence Labeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09913","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":"sha256:16c96b14f0cd5dfe102d78c7cc9a27ca26db8972b4df12a699ce5d854149d53c","target":"record","created_at":"2026-07-05T03:07:59Z","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":"c6dd74ab01274ff1dbc45f09211c65d2b4761ff761fa6b33893e7030dee58089","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-23T03:48:27Z","title_canon_sha256":"dad66ada63075029866cb897d7c47cf385fab47dead7e90c201b9f39fbc3bd56"},"schema_version":"1.0","source":{"id":"2108.09913","kind":"arxiv","version":1}},"canonical_sha256":"0490a8bb4373ff648769861d71d2dedef2d765a4ceccf81726fa87a0425166e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0490a8bb4373ff648769861d71d2dedef2d765a4ceccf81726fa87a0425166e3","first_computed_at":"2026-07-05T03:07:59.819872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:07:59.819872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AbaeRcPgzv02x/PouKR8x2NoWH5EVtWI3qGW8Q4GBrf5pHEYRazL5MR10HOmgGs0o7oYxveMfzBhwpk8WX7SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:07:59.820272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.09913","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16c96b14f0cd5dfe102d78c7cc9a27ca26db8972b4df12a699ce5d854149d53c","sha256:86075bc69d3a62428497ca547f3e36e8cb58ce71cdecd0946f293012327565f8"],"state_sha256":"f53e81e93e62365584111c635202de7304a1fb2c0f87c6ea135a98313d163310"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9VYiycYAWXEZI2ehBOZA790xPPn/o38b2nBTZe+pMiGRwZF/zqD62lfhHHICJlcr6zILZxcmAWvjIpVzAztBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:12:56.107576Z","bundle_sha256":"bcd99587d4665ce3a4bed851617acb62d0237de9f0934e97da362b9cc03c9e47"}}