{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PPSW4AZN42FOAIBJAZVC7HRCCR","short_pith_number":"pith:PPSW4AZN","schema_version":"1.0","canonical_sha256":"7be56e032de68ae02029066a2f9e22145a576dcb0142f101acd7a7779c1e4bab","source":{"kind":"arxiv","id":"2505.11582","version":2},"attestation_state":"computed","paper":{"title":"Comparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lee Harris","submitted_at":"2025-05-16T17:06:35Z","abstract_excerpt":"Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus on optimising speed and predictive accuracy. This is often achieved through neural methods that aim to learn language semantics. However, our results suggest that these are not always the best solution. Our task was to classify rigidly-structured medical documents according to their content, and we found that using off-the-shelf semantic vector search produced slightly worse pr"},"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":"2505.11582","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-16T17:06:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4832d76f1f42cd9fc84e9119a0917987720ab8de706271281dc9d1b3b96ee2e8","abstract_canon_sha256":"397effe7b9f9d00fb5df5335db889eb7034045c577c958fa9f70aa1ff93a15b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:59.698400Z","signature_b64":"ymSfHGV4XhgZirBtc3kpi9ntB4n6JS3HY0dLUplnF1grjerixozmgZiyEgM57yjPlDq7cBoMz+DwvWgaSvqgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be56e032de68ae02029066a2f9e22145a576dcb0142f101acd7a7779c1e4bab","last_reissued_at":"2026-07-05T11:14:59.697822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:59.697822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Lee Harris","submitted_at":"2025-05-16T17:06:35Z","abstract_excerpt":"Classification is a common AI problem, and vector search is a typical solution. This transforms a given body of text into a numerical representation, known as an embedding, and modern improvements to vector search focus on optimising speed and predictive accuracy. This is often achieved through neural methods that aim to learn language semantics. However, our results suggest that these are not always the best solution. Our task was to classify rigidly-structured medical documents according to their content, and we found that using off-the-shelf semantic vector search produced slightly worse pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11582","kind":"arxiv","version":2},"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/2505.11582/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.11582","created_at":"2026-07-05T11:14:59.697883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11582v2","created_at":"2026-07-05T11:14:59.697883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11582","created_at":"2026-07-05T11:14:59.697883+00:00"},{"alias_kind":"pith_short_12","alias_value":"PPSW4AZN42FO","created_at":"2026-07-05T11:14:59.697883+00:00"},{"alias_kind":"pith_short_16","alias_value":"PPSW4AZN42FOAIBJ","created_at":"2026-07-05T11:14:59.697883+00:00"},{"alias_kind":"pith_short_8","alias_value":"PPSW4AZN","created_at":"2026-07-05T11:14:59.697883+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/PPSW4AZN42FOAIBJAZVC7HRCCR","json":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR.json","graph_json":"https://pith.science/api/pith-number/PPSW4AZN42FOAIBJAZVC7HRCCR/graph.json","events_json":"https://pith.science/api/pith-number/PPSW4AZN42FOAIBJAZVC7HRCCR/events.json","paper":"https://pith.science/paper/PPSW4AZN"},"agent_actions":{"view_html":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR","download_json":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR.json","view_paper":"https://pith.science/paper/PPSW4AZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11582&json=true","fetch_graph":"https://pith.science/api/pith-number/PPSW4AZN42FOAIBJAZVC7HRCCR/graph.json","fetch_events":"https://pith.science/api/pith-number/PPSW4AZN42FOAIBJAZVC7HRCCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR/action/storage_attestation","attest_author":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR/action/author_attestation","sign_citation":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR/action/citation_signature","submit_replication":"https://pith.science/pith/PPSW4AZN42FOAIBJAZVC7HRCCR/action/replication_record"}},"created_at":"2026-07-05T11:14:59.697883+00:00","updated_at":"2026-07-05T11:14:59.697883+00:00"}