{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:MAF4IF37O42ZUQCHL6UERQDBIS","short_pith_number":"pith:MAF4IF37","schema_version":"1.0","canonical_sha256":"600bc4177f77359a40475fa848c061448fb16fa0e2464203f570c98c50cfa1ff","source":{"kind":"arxiv","id":"1511.06285","version":1},"attestation_state":"computed","paper":{"title":"Harvesting comparable corpora and mining them for equivalent bilingual sentences using statistical classification and analogy- based heuristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Emilia Rejmund, Krzysztof Marasek, Krzysztof Wo{\\l}k","submitted_at":"2015-11-18T15:26:06Z","abstract_excerpt":"Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our new methodologies for mining such data from previously obtained comparable corpora. The task is highly practical since non-parallel multilingual data exist in far greater quantities than parallel corpora, but parallel sentences are a much more useful resource. Here we propose a web crawling method for building subject-aligned comparable corpora from e.g. Wikipedia dumps and Euronews web page. The improve"},"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":"1511.06285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-11-18T15:26:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"37940c400d5284142f489542640da61f17221a3fb14bb5b0f9508e3f8ad425da","abstract_canon_sha256":"e4708663d21f734cac5a20d65fd938897ad17ab5126ad7b4603daa8b3efa6d92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:25.960889Z","signature_b64":"OrU0Fsazzo9r6GnVxwjeNT8vGIVpf+DEe9oiNStxS+DfNQ2bTU+Rhr3c7kLVHDWGhXrC9QndJxmyt3f2dtd5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"600bc4177f77359a40475fa848c061448fb16fa0e2464203f570c98c50cfa1ff","last_reissued_at":"2026-05-18T01:26:25.960525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:25.960525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harvesting comparable corpora and mining them for equivalent bilingual sentences using statistical classification and analogy- based heuristics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Emilia Rejmund, Krzysztof Marasek, Krzysztof Wo{\\l}k","submitted_at":"2015-11-18T15:26:06Z","abstract_excerpt":"Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our new methodologies for mining such data from previously obtained comparable corpora. The task is highly practical since non-parallel multilingual data exist in far greater quantities than parallel corpora, but parallel sentences are a much more useful resource. Here we propose a web crawling method for building subject-aligned comparable corpora from e.g. Wikipedia dumps and Euronews web page. The improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06285","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":"1511.06285","created_at":"2026-05-18T01:26:25.960580+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06285v1","created_at":"2026-05-18T01:26:25.960580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06285","created_at":"2026-05-18T01:26:25.960580+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAF4IF37O42Z","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAF4IF37O42ZUQCH","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAF4IF37","created_at":"2026-05-18T12:29:32.376354+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/MAF4IF37O42ZUQCHL6UERQDBIS","json":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS.json","graph_json":"https://pith.science/api/pith-number/MAF4IF37O42ZUQCHL6UERQDBIS/graph.json","events_json":"https://pith.science/api/pith-number/MAF4IF37O42ZUQCHL6UERQDBIS/events.json","paper":"https://pith.science/paper/MAF4IF37"},"agent_actions":{"view_html":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS","download_json":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS.json","view_paper":"https://pith.science/paper/MAF4IF37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06285&json=true","fetch_graph":"https://pith.science/api/pith-number/MAF4IF37O42ZUQCHL6UERQDBIS/graph.json","fetch_events":"https://pith.science/api/pith-number/MAF4IF37O42ZUQCHL6UERQDBIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS/action/storage_attestation","attest_author":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS/action/author_attestation","sign_citation":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS/action/citation_signature","submit_replication":"https://pith.science/pith/MAF4IF37O42ZUQCHL6UERQDBIS/action/replication_record"}},"created_at":"2026-05-18T01:26:25.960580+00:00","updated_at":"2026-05-18T01:26:25.960580+00:00"}