{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IX4LF25CNSLHN242D46G3A2QVB","short_pith_number":"pith:IX4LF25C","schema_version":"1.0","canonical_sha256":"45f8b2eba26c9676eb9a1f3c6d8350a864c2fcbac5e9fb1a7146cfc860e0375b","source":{"kind":"arxiv","id":"1904.02181","version":1},"attestation_state":"computed","paper":{"title":"Probing Biomedical Embeddings from Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Qiao Jin, William W. Cohen, Xinghua Lu","submitted_at":"2019-04-03T18:05:02Z","abstract_excerpt":"Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance. In this paper, we conduct probing experiments to determine what additional information is carried intrinsically by the in-domain trained contextualized embeddings. For this we use the pre-trained LMs as fixed feature extractors and restrict the downstream task models to not have additional sequence modeling layers. We compare BERT, ELMo, BioBERT and BioELMo, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.02181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-03T18:05:02Z","cross_cats_sorted":[],"title_canon_sha256":"e10bd1b33dc48679ccd600f7dc69ecf4fff8c828f9dc80b90e6610275506ce32","abstract_canon_sha256":"48aa5b812a81f8168810e48d825aab0dd7cbebf1f710431971bd9701043f6bbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:24.259601Z","signature_b64":"zlEAgbzAx1ilgVZKYnsEg2R2zl0p80++L1tF3odw1oA4/kYdpPY64IhC0szBqej8nqS9Td7J5f9njBfzwTrLBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f8b2eba26c9676eb9a1f3c6d8350a864c2fcbac5e9fb1a7146cfc860e0375b","last_reissued_at":"2026-05-17T23:49:24.259184Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:24.259184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Biomedical Embeddings from Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bhuwan Dhingra, Qiao Jin, William W. Cohen, Xinghua Lu","submitted_at":"2019-04-03T18:05:02Z","abstract_excerpt":"Contextualized word embeddings derived from pre-trained language models (LMs) show significant improvements on downstream NLP tasks. Pre-training on domain-specific corpora, such as biomedical articles, further improves their performance. In this paper, we conduct probing experiments to determine what additional information is carried intrinsically by the in-domain trained contextualized embeddings. For this we use the pre-trained LMs as fixed feature extractors and restrict the downstream task models to not have additional sequence modeling layers. We compare BERT, ELMo, BioBERT and BioELMo, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.02181","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.02181","created_at":"2026-05-17T23:49:24.259248+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.02181v1","created_at":"2026-05-17T23:49:24.259248+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.02181","created_at":"2026-05-17T23:49:24.259248+00:00"},{"alias_kind":"pith_short_12","alias_value":"IX4LF25CNSLH","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IX4LF25CNSLHN242","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IX4LF25C","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB","json":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB.json","graph_json":"https://pith.science/api/pith-number/IX4LF25CNSLHN242D46G3A2QVB/graph.json","events_json":"https://pith.science/api/pith-number/IX4LF25CNSLHN242D46G3A2QVB/events.json","paper":"https://pith.science/paper/IX4LF25C"},"agent_actions":{"view_html":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB","download_json":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB.json","view_paper":"https://pith.science/paper/IX4LF25C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.02181&json=true","fetch_graph":"https://pith.science/api/pith-number/IX4LF25CNSLHN242D46G3A2QVB/graph.json","fetch_events":"https://pith.science/api/pith-number/IX4LF25CNSLHN242D46G3A2QVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB/action/storage_attestation","attest_author":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB/action/author_attestation","sign_citation":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB/action/citation_signature","submit_replication":"https://pith.science/pith/IX4LF25CNSLHN242D46G3A2QVB/action/replication_record"}},"created_at":"2026-05-17T23:49:24.259248+00:00","updated_at":"2026-05-17T23:49:24.259248+00:00"}