{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3MMNWZEQYNBAPPSHLVA2DHU2X5","short_pith_number":"pith:3MMNWZEQ","schema_version":"1.0","canonical_sha256":"db18db6490c34207be475d41a19e9abf5dce94d914dd180ade4047af354331b2","source":{"kind":"arxiv","id":"1708.03181","version":1},"attestation_state":"computed","paper":{"title":"Utilizing Embeddings for Ad-hoc Retrieval by Document-to-document Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ben He, Chenhao Yang, Yanhua Ran","submitted_at":"2017-08-10T12:33:25Z","abstract_excerpt":"Latent semantic representations of words or paragraphs, namely the embeddings, have been widely applied to information retrieval (IR). One of the common approaches of utilizing embeddings for IR is to estimate the document-to-query (D2Q) similarity in their embeddings. As words with similar syntactic usage are usually very close to each other in the embeddings space, although they are not semantically similar, the D2Q similarity approach may suffer from the problem of \"multiple degrees of similarity\". To this end, this paper proposes a novel approach that estimates a semantic relevance score ("},"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":"1708.03181","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-10T12:33:25Z","cross_cats_sorted":[],"title_canon_sha256":"a8da08e534d0491bb4d73600995a89249a9da79818a4bfe8139623c8cad7f926","abstract_canon_sha256":"e08fd584d32ff48af86fedb92e0f4aea6d44115c3929a686f656bfbbd2eba630"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:14.543758Z","signature_b64":"qqBAvLdbVAOWrPboDqYtaFCtofy/b3f1sLgP8f/2Px2O+pJdM3jBSSEBKUeKcJ+m8IdN0E8XsL2sBb3nvpI8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db18db6490c34207be475d41a19e9abf5dce94d914dd180ade4047af354331b2","last_reissued_at":"2026-05-18T00:38:14.543014Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:14.543014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Utilizing Embeddings for Ad-hoc Retrieval by Document-to-document Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ben He, Chenhao Yang, Yanhua Ran","submitted_at":"2017-08-10T12:33:25Z","abstract_excerpt":"Latent semantic representations of words or paragraphs, namely the embeddings, have been widely applied to information retrieval (IR). One of the common approaches of utilizing embeddings for IR is to estimate the document-to-query (D2Q) similarity in their embeddings. As words with similar syntactic usage are usually very close to each other in the embeddings space, although they are not semantically similar, the D2Q similarity approach may suffer from the problem of \"multiple degrees of similarity\". To this end, this paper proposes a novel approach that estimates a semantic relevance score ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03181","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":"1708.03181","created_at":"2026-05-18T00:38:14.543148+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.03181v1","created_at":"2026-05-18T00:38:14.543148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03181","created_at":"2026-05-18T00:38:14.543148+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MMNWZEQYNBA","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MMNWZEQYNBAPPSH","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MMNWZEQ","created_at":"2026-05-18T12:30:58.224056+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/3MMNWZEQYNBAPPSHLVA2DHU2X5","json":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5.json","graph_json":"https://pith.science/api/pith-number/3MMNWZEQYNBAPPSHLVA2DHU2X5/graph.json","events_json":"https://pith.science/api/pith-number/3MMNWZEQYNBAPPSHLVA2DHU2X5/events.json","paper":"https://pith.science/paper/3MMNWZEQ"},"agent_actions":{"view_html":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5","download_json":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5.json","view_paper":"https://pith.science/paper/3MMNWZEQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.03181&json=true","fetch_graph":"https://pith.science/api/pith-number/3MMNWZEQYNBAPPSHLVA2DHU2X5/graph.json","fetch_events":"https://pith.science/api/pith-number/3MMNWZEQYNBAPPSHLVA2DHU2X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5/action/storage_attestation","attest_author":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5/action/author_attestation","sign_citation":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5/action/citation_signature","submit_replication":"https://pith.science/pith/3MMNWZEQYNBAPPSHLVA2DHU2X5/action/replication_record"}},"created_at":"2026-05-18T00:38:14.543148+00:00","updated_at":"2026-05-18T00:38:14.543148+00:00"}