{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BD3VOUPKMC554FXBXQAWPHSUF2","short_pith_number":"pith:BD3VOUPK","schema_version":"1.0","canonical_sha256":"08f75751ea60bbde16e1bc01679e542e918b591d19627bec3b20e64d0dbe568a","source":{"kind":"arxiv","id":"1608.01972","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Gap: Incorporating a Semantic Similarity Measure for Effectively Mapping PubMed Queries to Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Nicolas Fiorini, Sun Kim, W. John Wilbur, Zhiyong Lu","submitted_at":"2016-08-05T18:53:42Z","abstract_excerpt":"The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words from a query are found. The semantic analysis methods such as LSA (latent semantic analysis) and LDA (latent Dirichlet allocation) have been proposed to address the issue, but their performance is not superior compared to common IR approaches. Here we present a query-document similarity measure motivated by the Word Mover's Distance. Unlike other similarity me"},"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":"1608.01972","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-05T18:53:42Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"5866313e42334193d34b6a705fc9b751472d6be0bb271682d725f04d27d76b4e","abstract_canon_sha256":"80b7f22c513a02f644056b3621be9c1e7147ea3c95e3200caeaff1f7610f7e13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:36.463036Z","signature_b64":"YXSuHo+s7YnFc21ILsqFpy3wUsX+VJGHLp8+2nW7fKrtTv0d4vJKOk3yMUa8yc99CMeUQZi7kuosKz3rfCS2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08f75751ea60bbde16e1bc01679e542e918b591d19627bec3b20e64d0dbe568a","last_reissued_at":"2026-05-18T00:32:36.462211Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:36.462211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap: Incorporating a Semantic Similarity Measure for Effectively Mapping PubMed Queries to Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Nicolas Fiorini, Sun Kim, W. John Wilbur, Zhiyong Lu","submitted_at":"2016-08-05T18:53:42Z","abstract_excerpt":"The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words from a query are found. The semantic analysis methods such as LSA (latent semantic analysis) and LDA (latent Dirichlet allocation) have been proposed to address the issue, but their performance is not superior compared to common IR approaches. Here we present a query-document similarity measure motivated by the Word Mover's Distance. Unlike other similarity me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.01972","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":""},"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":"1608.01972","created_at":"2026-05-18T00:32:36.462372+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.01972v2","created_at":"2026-05-18T00:32:36.462372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.01972","created_at":"2026-05-18T00:32:36.462372+00:00"},{"alias_kind":"pith_short_12","alias_value":"BD3VOUPKMC55","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BD3VOUPKMC554FXB","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BD3VOUPK","created_at":"2026-05-18T12:30:07.202191+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/BD3VOUPKMC554FXBXQAWPHSUF2","json":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2.json","graph_json":"https://pith.science/api/pith-number/BD3VOUPKMC554FXBXQAWPHSUF2/graph.json","events_json":"https://pith.science/api/pith-number/BD3VOUPKMC554FXBXQAWPHSUF2/events.json","paper":"https://pith.science/paper/BD3VOUPK"},"agent_actions":{"view_html":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2","download_json":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2.json","view_paper":"https://pith.science/paper/BD3VOUPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.01972&json=true","fetch_graph":"https://pith.science/api/pith-number/BD3VOUPKMC554FXBXQAWPHSUF2/graph.json","fetch_events":"https://pith.science/api/pith-number/BD3VOUPKMC554FXBXQAWPHSUF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2/action/storage_attestation","attest_author":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2/action/author_attestation","sign_citation":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2/action/citation_signature","submit_replication":"https://pith.science/pith/BD3VOUPKMC554FXBXQAWPHSUF2/action/replication_record"}},"created_at":"2026-05-18T00:32:36.462372+00:00","updated_at":"2026-05-18T00:32:36.462372+00:00"}