{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5U4E4RVFJ4C4LFRK4Y7YDIHUD6","short_pith_number":"pith:5U4E4RVF","canonical_record":{"source":{"id":"1906.00282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T20:07:11Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"2bcd0a14c1e32ebfa36600d3f2007c91fce31dbbc996f49b2868f1c985e23f4f","abstract_canon_sha256":"118f2f0f83f0f97343babc61f2e19538bff7a520ab2b7a1eec9213da8e46a2bb"},"schema_version":"1.0"},"canonical_sha256":"ed384e46a54f05c5962ae63f81a0f41fb52f0c8a795103a18b7c622ceb15b6b5","source":{"kind":"arxiv","id":"1906.00282","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00282","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00282v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00282","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"5U4E4RVFJ4C4","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5U4E4RVFJ4C4LFRK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5U4E4RVF","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5U4E4RVFJ4C4LFRK4Y7YDIHUD6","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T20:07:11Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"2bcd0a14c1e32ebfa36600d3f2007c91fce31dbbc996f49b2868f1c985e23f4f","abstract_canon_sha256":"118f2f0f83f0f97343babc61f2e19538bff7a520ab2b7a1eec9213da8e46a2bb"},"schema_version":"1.0"},"canonical_sha256":"ed384e46a54f05c5962ae63f81a0f41fb52f0c8a795103a18b7c622ceb15b6b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:27.607702Z","signature_b64":"vNWGmUU2okQ50KrONNzMfHjsdeO7+KtlAALEQ5XyJMGjYwoTHbNV5IRjIXoD3g6QonO7LzElZpUyKWDjJT88Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed384e46a54f05c5962ae63f81a0f41fb52f0c8a795103a18b7c622ceb15b6b5","last_reissued_at":"2026-05-17T23:44:27.607162Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:27.607162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00282","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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Fd1qAgjl13vuJGIisaPPwi5PKtXs0qM6s3Au7JaDCTy7/pvt10AHDqyao7aKM+IqeDaAQNBL9OYNtU+YdUiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:28:43.886527Z"},"content_sha256":"6a5ac2294166fd82c9d1251bf8bc5944959e03f0cd036213e1b1e99a7b35a7a1","schema_version":"1.0","event_id":"sha256:6a5ac2294166fd82c9d1251bf8bc5944959e03f0cd036213e1b1e99a7b35a7a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5U4E4RVFJ4C4LFRK4Y7YDIHUD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Joel Mathew, Jos\\'e Luis Ambite, Shobeir Fakhraei","submitted_at":"2019-06-01T20:07:11Z","abstract_excerpt":"We present a weakly-supervised data augmentation approach to improve Named Entity Recognition (NER) in a challenging domain: extracting biomedical entities (e.g., proteins) from the scientific literature. First, we train a neural NER (NNER) model over a small seed of fully-labeled examples. Second, we use a reference set of entity names (e.g., proteins in UniProt) to identify entity mentions with high precision, but low recall, on an unlabeled corpus. Third, we use the NNER model to assign weak labels to the corpus. Finally, we retrain our NNER model iteratively over the augmented training set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00282","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":"2026-05-17T23:44:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gVIcxcfq927usTgjVtQBgG2/3/rVyqtRNvDujlT24qrVMB9lD8QT5/gaJy0atm7LkymhLF/umwJmGdxIlmoqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T09:28:43.886876Z"},"content_sha256":"f06aaee6ce6677a57827ebdc172fd9c0d2ff3ff6bb013fb24c77dee1568fff98","schema_version":"1.0","event_id":"sha256:f06aaee6ce6677a57827ebdc172fd9c0d2ff3ff6bb013fb24c77dee1568fff98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6/bundle.json","state_url":"https://pith.science/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6/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":"2026-06-05T09:28:43Z","links":{"resolver":"https://pith.science/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6","bundle":"https://pith.science/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6/bundle.json","state":"https://pith.science/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5U4E4RVFJ4C4LFRK4Y7YDIHUD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5U4E4RVFJ4C4LFRK4Y7YDIHUD6","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":"118f2f0f83f0f97343babc61f2e19538bff7a520ab2b7a1eec9213da8e46a2bb","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T20:07:11Z","title_canon_sha256":"2bcd0a14c1e32ebfa36600d3f2007c91fce31dbbc996f49b2868f1c985e23f4f"},"schema_version":"1.0","source":{"id":"1906.00282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00282","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00282v1","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00282","created_at":"2026-05-17T23:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"5U4E4RVFJ4C4","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5U4E4RVFJ4C4LFRK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5U4E4RVF","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:f06aaee6ce6677a57827ebdc172fd9c0d2ff3ff6bb013fb24c77dee1568fff98","target":"graph","created_at":"2026-05-17T23:44:27Z","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 present a weakly-supervised data augmentation approach to improve Named Entity Recognition (NER) in a challenging domain: extracting biomedical entities (e.g., proteins) from the scientific literature. First, we train a neural NER (NNER) model over a small seed of fully-labeled examples. Second, we use a reference set of entity names (e.g., proteins in UniProt) to identify entity mentions with high precision, but low recall, on an unlabeled corpus. Third, we use the NNER model to assign weak labels to the corpus. Finally, we retrain our NNER model iteratively over the augmented training set","authors_text":"Joel Mathew, Jos\\'e Luis Ambite, Shobeir Fakhraei","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T20:07:11Z","title":"Biomedical Named Entity Recognition via Reference-Set Augmented Bootstrapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00282","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":"sha256:6a5ac2294166fd82c9d1251bf8bc5944959e03f0cd036213e1b1e99a7b35a7a1","target":"record","created_at":"2026-05-17T23:44:27Z","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":"118f2f0f83f0f97343babc61f2e19538bff7a520ab2b7a1eec9213da8e46a2bb","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-01T20:07:11Z","title_canon_sha256":"2bcd0a14c1e32ebfa36600d3f2007c91fce31dbbc996f49b2868f1c985e23f4f"},"schema_version":"1.0","source":{"id":"1906.00282","kind":"arxiv","version":1}},"canonical_sha256":"ed384e46a54f05c5962ae63f81a0f41fb52f0c8a795103a18b7c622ceb15b6b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed384e46a54f05c5962ae63f81a0f41fb52f0c8a795103a18b7c622ceb15b6b5","first_computed_at":"2026-05-17T23:44:27.607162Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:27.607162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vNWGmUU2okQ50KrONNzMfHjsdeO7+KtlAALEQ5XyJMGjYwoTHbNV5IRjIXoD3g6QonO7LzElZpUyKWDjJT88Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:27.607702Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a5ac2294166fd82c9d1251bf8bc5944959e03f0cd036213e1b1e99a7b35a7a1","sha256:f06aaee6ce6677a57827ebdc172fd9c0d2ff3ff6bb013fb24c77dee1568fff98"],"state_sha256":"91d4f924144dd1442a2ad6235a1bacb2d22c0dd655eda090a4fe6595805601b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D4yGb8TZ4O1e7zozaR2JgDkQAtEWSdgfA75jhTcaNKxgzn9BNjKRiMpTIEviehdUTFyxSC4GYBW6jggMpB40Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T09:28:43.888859Z","bundle_sha256":"e67a91fb4a45b1355c487d689b45d7016906559c246529c47aef77f30a101bff"}}