{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:EUUMA6VFATSMCFTQ6CPGFG3AB7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2097aede9bb720abb9417858ae1f707b44aeec8370756e9d319b81c5ee0f6f1c","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T18:35:49Z","title_canon_sha256":"1a3bb08e615104954b5a08b5fc1d567120371629e9be7152d1a2e0544c723dfd"},"schema_version":"1.0","source":{"id":"1509.08881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.08881","created_at":"2026-05-18T01:31:46Z"},{"alias_kind":"arxiv_version","alias_value":"1509.08881v1","created_at":"2026-05-18T01:31:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.08881","created_at":"2026-05-18T01:31:46Z"},{"alias_kind":"pith_short_12","alias_value":"EUUMA6VFATSM","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EUUMA6VFATSMCFTQ","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EUUMA6VF","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:b1e5af4b7cf15c834309e9fc037dfc5d7baeddb1ddae953783ce903bbd05cb5c","target":"graph","created_at":"2026-05-18T01:31:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 methodology 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 Wikipedia articles. We also introduce a method for extracting","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","cross_cats":["cs.IR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T18:35:49Z","title":"Building Subject-aligned Comparable Corpora and Mining it for Truly Parallel Sentence Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.08881","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:78bdf1ea45588d26532831aa92031c073ef2d21d7a76c9d9db793405770c2b4b","target":"record","created_at":"2026-05-18T01:31:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2097aede9bb720abb9417858ae1f707b44aeec8370756e9d319b81c5ee0f6f1c","cross_cats_sorted":["cs.IR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T18:35:49Z","title_canon_sha256":"1a3bb08e615104954b5a08b5fc1d567120371629e9be7152d1a2e0544c723dfd"},"schema_version":"1.0","source":{"id":"1509.08881","kind":"arxiv","version":1}},"canonical_sha256":"2528c07aa504e4c11670f09e629b600fc73f970cf0907d56eaf5b530d0211077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2528c07aa504e4c11670f09e629b600fc73f970cf0907d56eaf5b530d0211077","first_computed_at":"2026-05-18T01:31:46.919947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:31:46.919947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fI9a3uo79DUQMRquYzZWT2TFzX1S+tNw+bHMxlFKBIKjO3JjfoJvvUCNm+YQ51Im827K4vBzNyVBDcBeuugUDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:31:46.920394Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.08881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78bdf1ea45588d26532831aa92031c073ef2d21d7a76c9d9db793405770c2b4b","sha256:b1e5af4b7cf15c834309e9fc037dfc5d7baeddb1ddae953783ce903bbd05cb5c"],"state_sha256":"9554deb4e18a6437191b80a671dd0cabd92456f51ad7016e0605cec8a2b1da3c"}