{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:6NVQOKYR2QAZDASIO76EBVPSDL","short_pith_number":"pith:6NVQOKYR","schema_version":"1.0","canonical_sha256":"f36b072b11d40191824877fc40d5f21ac47778cd0600442b5c9ec62698906fce","source":{"kind":"arxiv","id":"1512.01641","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised comparable corpora preparation and exploration for bi-lingual translation equivalents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","submitted_at":"2015-12-05T08:59:28Z","abstract_excerpt":"The multilingual nature of the world makes translation a crucial requirement today. Parallel dictionaries constructed by humans are a widely-available resource, but they are limited and do not provide enough coverage for good quality translation purposes, due to out-of-vocabulary words and neologisms. This motivates the use of statistical translation systems, which are unfortunately dependent on the quantity and quality of training data. Such systems have a very limited availability especially for some languages and very narrow text domains. In this research we present our improvements to curr"},"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":"1512.01641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:59:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"70d5a90f51a8d3feca9368968f1ddbed353eff0fc7546929df502fa64f988f4e","abstract_canon_sha256":"70250c91bbde027709062bb2167d34ae659be8f8a7f2f3b2aee0ed3dcfd3e99c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:09.272171Z","signature_b64":"O6uv3S07LFG7ad4WST3wc+HhPZKnwPIgyN5yfc/Pvu4IWGLCNI388bfx7WmIgSbl55yn0TJL2iX3qNnxwlcCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f36b072b11d40191824877fc40d5f21ac47778cd0600442b5c9ec62698906fce","last_reissued_at":"2026-05-18T01:25:09.271493Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:09.271493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised comparable corpora preparation and exploration for bi-lingual translation equivalents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","submitted_at":"2015-12-05T08:59:28Z","abstract_excerpt":"The multilingual nature of the world makes translation a crucial requirement today. Parallel dictionaries constructed by humans are a widely-available resource, but they are limited and do not provide enough coverage for good quality translation purposes, due to out-of-vocabulary words and neologisms. This motivates the use of statistical translation systems, which are unfortunately dependent on the quantity and quality of training data. Such systems have a very limited availability especially for some languages and very narrow text domains. In this research we present our improvements to curr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01641","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":"1512.01641","created_at":"2026-05-18T01:25:09.271608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.01641v1","created_at":"2026-05-18T01:25:09.271608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01641","created_at":"2026-05-18T01:25:09.271608+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NVQOKYR2QAZ","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NVQOKYR2QAZDASI","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NVQOKYR","created_at":"2026-05-18T12:29:07.941421+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/6NVQOKYR2QAZDASIO76EBVPSDL","json":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL.json","graph_json":"https://pith.science/api/pith-number/6NVQOKYR2QAZDASIO76EBVPSDL/graph.json","events_json":"https://pith.science/api/pith-number/6NVQOKYR2QAZDASIO76EBVPSDL/events.json","paper":"https://pith.science/paper/6NVQOKYR"},"agent_actions":{"view_html":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL","download_json":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL.json","view_paper":"https://pith.science/paper/6NVQOKYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.01641&json=true","fetch_graph":"https://pith.science/api/pith-number/6NVQOKYR2QAZDASIO76EBVPSDL/graph.json","fetch_events":"https://pith.science/api/pith-number/6NVQOKYR2QAZDASIO76EBVPSDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/action/storage_attestation","attest_author":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/action/author_attestation","sign_citation":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/action/citation_signature","submit_replication":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/action/replication_record"}},"created_at":"2026-05-18T01:25:09.271608+00:00","updated_at":"2026-05-18T01:25:09.271608+00:00"}