{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JMGM5ZXQ2EYGF3MNPEXWIHVLRK","short_pith_number":"pith:JMGM5ZXQ","schema_version":"1.0","canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","source":{"kind":"arxiv","id":"1805.04437","version":1},"attestation_state":"computed","paper":{"title":"Cross-lingual Document Retrieval using Regularized Wasserstein Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Charlotte Laclau, Georgios Balikas, Ievgen Redko, Massih-Reza Amini","submitted_at":"2018-05-11T15:01:00Z","abstract_excerpt":"Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence between text passages. In this paper, we demonstrate that this metric can be extended to incorporate term-weighting schemes and provide more accurate and computationally efficient matching between documents using entropic regularization. We evaluate the benefits of both extensions in the task of cross-lingual document retrieval (CLDR). Our experimental resu"},"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":"1805.04437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-11T15:01:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"679345c8e32424896af6be48dfd65b71d3284d28496016f615b2ac486a5101bb","abstract_canon_sha256":"693816d909707df7ca79c9fe21683277ea282c43589e42952308b5505c1af57a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:10.338640Z","signature_b64":"KVQjJ+pN9lN6eCIc8mF9yxPXgeI0VVtVunnlISE2rNx/9WfmRlpSLSgoVI9sWXUwCgjk1rKKITbLzvRpkxIWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","last_reissued_at":"2026-05-18T00:16:10.338052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:10.338052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-lingual Document Retrieval using Regularized Wasserstein Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Charlotte Laclau, Georgios Balikas, Ievgen Redko, Massih-Reza Amini","submitted_at":"2018-05-11T15:01:00Z","abstract_excerpt":"Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence between text passages. In this paper, we demonstrate that this metric can be extended to incorporate term-weighting schemes and provide more accurate and computationally efficient matching between documents using entropic regularization. We evaluate the benefits of both extensions in the task of cross-lingual document retrieval (CLDR). Our experimental resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04437","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":"1805.04437","created_at":"2026-05-18T00:16:10.338142+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04437v1","created_at":"2026-05-18T00:16:10.338142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04437","created_at":"2026-05-18T00:16:10.338142+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMGM5ZXQ2EYG","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMGM5ZXQ2EYGF3MN","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMGM5ZXQ","created_at":"2026-05-18T12:32:31.084164+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/JMGM5ZXQ2EYGF3MNPEXWIHVLRK","json":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK.json","graph_json":"https://pith.science/api/pith-number/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/graph.json","events_json":"https://pith.science/api/pith-number/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/events.json","paper":"https://pith.science/paper/JMGM5ZXQ"},"agent_actions":{"view_html":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK","download_json":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK.json","view_paper":"https://pith.science/paper/JMGM5ZXQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04437&json=true","fetch_graph":"https://pith.science/api/pith-number/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/graph.json","fetch_events":"https://pith.science/api/pith-number/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/action/storage_attestation","attest_author":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/action/author_attestation","sign_citation":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/action/citation_signature","submit_replication":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/action/replication_record"}},"created_at":"2026-05-18T00:16:10.338142+00:00","updated_at":"2026-05-18T00:16:10.338142+00:00"}