{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7R4SOQL4Y2VVB2JS6DKMKMRF5X","short_pith_number":"pith:7R4SOQL4","schema_version":"1.0","canonical_sha256":"fc7927417cc6ab50e932f0d4c53225edc6970f3d43165c5db26792d6f1355478","source":{"kind":"arxiv","id":"1906.05468","version":1},"attestation_state":"computed","paper":{"title":"A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aditya Joshi, Cecile Paris, C Raina MacIntyre, Ross Sparks, Sarvnaz Karimi","submitted_at":"2019-06-13T03:48:34Z","abstract_excerpt":"Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better t"},"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":"1906.05468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-13T03:48:34Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"02039f8bf12a864752b7d7b1d87d7472001c637e345584c1d0270e0548863623","abstract_canon_sha256":"33cef3c9838633f5ab1b8a0c4ac4450aa193579a79451194f69855a2c4ea9e01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:25.275366Z","signature_b64":"ZxdIwuffoojWu4Fg7PktaShxNaxCtlfS0TkPKMzT0utbkwL9PzcelwGsQtA5vEfB5d4WeXSmBqQ7L16zIy/YAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc7927417cc6ab50e932f0d4c53225edc6970f3d43165c5db26792d6f1355478","last_reissued_at":"2026-05-17T23:43:25.274875Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:25.274875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of Word-based and Context-based Representations for Classification Problems in Health Informatics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Aditya Joshi, Cecile Paris, C Raina MacIntyre, Ross Sparks, Sarvnaz Karimi","submitted_at":"2019-06-13T03:48:34Z","abstract_excerpt":"Distributed representations of text can be used as features when training a statistical classifier. These representations may be created as a composition of word vectors or as context-based sentence vectors. We compare the two kinds of representations (word versus context) for three classification problems: influenza infection classification, drug usage classification and personal health mention classification. For statistical classifiers trained for each of these problems, context-based representations based on ELMo, Universal Sentence Encoder, Neural-Net Language Model and FLAIR are better t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05468","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":"1906.05468","created_at":"2026-05-17T23:43:25.274954+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05468v1","created_at":"2026-05-17T23:43:25.274954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05468","created_at":"2026-05-17T23:43:25.274954+00:00"},{"alias_kind":"pith_short_12","alias_value":"7R4SOQL4Y2VV","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7R4SOQL4Y2VVB2JS","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7R4SOQL4","created_at":"2026-05-18T12:33:12.712433+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/7R4SOQL4Y2VVB2JS6DKMKMRF5X","json":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X.json","graph_json":"https://pith.science/api/pith-number/7R4SOQL4Y2VVB2JS6DKMKMRF5X/graph.json","events_json":"https://pith.science/api/pith-number/7R4SOQL4Y2VVB2JS6DKMKMRF5X/events.json","paper":"https://pith.science/paper/7R4SOQL4"},"agent_actions":{"view_html":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X","download_json":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X.json","view_paper":"https://pith.science/paper/7R4SOQL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05468&json=true","fetch_graph":"https://pith.science/api/pith-number/7R4SOQL4Y2VVB2JS6DKMKMRF5X/graph.json","fetch_events":"https://pith.science/api/pith-number/7R4SOQL4Y2VVB2JS6DKMKMRF5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X/action/storage_attestation","attest_author":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X/action/author_attestation","sign_citation":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X/action/citation_signature","submit_replication":"https://pith.science/pith/7R4SOQL4Y2VVB2JS6DKMKMRF5X/action/replication_record"}},"created_at":"2026-05-17T23:43:25.274954+00:00","updated_at":"2026-05-17T23:43:25.274954+00:00"}