{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5DYJDXJYPPHPKX6IQEWS7BBATK","short_pith_number":"pith:5DYJDXJY","schema_version":"1.0","canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","source":{"kind":"arxiv","id":"1804.10413","version":1},"attestation_state":"computed","paper":{"title":"Extracting Parallel Paragraphs from Common Crawl","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Irena Holubov\\'a, Jakub K\\'udela, Ond\\v{r}ej Bojar","submitted_at":"2018-04-27T09:33:49Z","abstract_excerpt":"Most of the current methods for mining parallel texts from the web assume that web pages of web sites share same structure across languages. We believe that there still exists a non-negligible amount of parallel data spread across sources not satisfying this assumption. We propose an approach based on a combination of bivec (a bilingual extension of word2vec) and locality-sensitive hashing which allows us to efficiently identify pairs of parallel segments located anywhere on pages of a given web domain, regardless their structure. We validate our method on realigning segments from a large para"},"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":"1804.10413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-27T09:33:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb261c8b2f83aa07feb03c505aef3c9100f9f966f9fe8eed1f35fb1a0023fc47","abstract_canon_sha256":"dac2160096da87e79ab5567001c327bc3629a146841b877ceff0b993a3b66bb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:20.856096Z","signature_b64":"TI8wdz+QVfEfAK4FwaJq1URwvY04k3m0nd30hkXv8fSPyzajkL3RdoTqww9FrBjH1kb/g6ViBtnOcjkCc6l3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","last_reissued_at":"2026-05-18T00:17:20.855392Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:20.855392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Parallel Paragraphs from Common Crawl","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Irena Holubov\\'a, Jakub K\\'udela, Ond\\v{r}ej Bojar","submitted_at":"2018-04-27T09:33:49Z","abstract_excerpt":"Most of the current methods for mining parallel texts from the web assume that web pages of web sites share same structure across languages. We believe that there still exists a non-negligible amount of parallel data spread across sources not satisfying this assumption. We propose an approach based on a combination of bivec (a bilingual extension of word2vec) and locality-sensitive hashing which allows us to efficiently identify pairs of parallel segments located anywhere on pages of a given web domain, regardless their structure. We validate our method on realigning segments from a large para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10413","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":"1804.10413","created_at":"2026-05-18T00:17:20.855498+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10413v1","created_at":"2026-05-18T00:17:20.855498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10413","created_at":"2026-05-18T00:17:20.855498+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DYJDXJYPPHP","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DYJDXJYPPHPKX6I","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DYJDXJY","created_at":"2026-05-18T12:32:08.215937+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/5DYJDXJYPPHPKX6IQEWS7BBATK","json":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK.json","graph_json":"https://pith.science/api/pith-number/5DYJDXJYPPHPKX6IQEWS7BBATK/graph.json","events_json":"https://pith.science/api/pith-number/5DYJDXJYPPHPKX6IQEWS7BBATK/events.json","paper":"https://pith.science/paper/5DYJDXJY"},"agent_actions":{"view_html":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK","download_json":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK.json","view_paper":"https://pith.science/paper/5DYJDXJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10413&json=true","fetch_graph":"https://pith.science/api/pith-number/5DYJDXJYPPHPKX6IQEWS7BBATK/graph.json","fetch_events":"https://pith.science/api/pith-number/5DYJDXJYPPHPKX6IQEWS7BBATK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/action/storage_attestation","attest_author":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/action/author_attestation","sign_citation":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/action/citation_signature","submit_replication":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/action/replication_record"}},"created_at":"2026-05-18T00:17:20.855498+00:00","updated_at":"2026-05-18T00:17:20.855498+00:00"}