{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6NVQOKYR2QAZDASIO76EBVPSDL","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":"70250c91bbde027709062bb2167d34ae659be8f8a7f2f3b2aee0ed3dcfd3e99c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:59:28Z","title_canon_sha256":"70d5a90f51a8d3feca9368968f1ddbed353eff0fc7546929df502fa64f988f4e"},"schema_version":"1.0","source":{"id":"1512.01641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01641","created_at":"2026-05-18T01:25:09Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01641v1","created_at":"2026-05-18T01:25:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01641","created_at":"2026-05-18T01:25:09Z"},{"alias_kind":"pith_short_12","alias_value":"6NVQOKYR2QAZ","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6NVQOKYR2QAZDASI","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6NVQOKYR","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:821c8a035cb31775f3d9b1d634436d61df6fb8967cb2f036cbee8772428c8768","target":"graph","created_at":"2026-05-18T01:25:09Z","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":"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","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:59:28Z","title":"Unsupervised comparable corpora preparation and exploration for bi-lingual translation equivalents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01641","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":"sha256:53ed574bfcf535af41140bfcd972e4fefee1ba19c06ea8d6ac684425da3e2a4a","target":"record","created_at":"2026-05-18T01:25:09Z","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":"70250c91bbde027709062bb2167d34ae659be8f8a7f2f3b2aee0ed3dcfd3e99c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-12-05T08:59:28Z","title_canon_sha256":"70d5a90f51a8d3feca9368968f1ddbed353eff0fc7546929df502fa64f988f4e"},"schema_version":"1.0","source":{"id":"1512.01641","kind":"arxiv","version":1}},"canonical_sha256":"f36b072b11d40191824877fc40d5f21ac47778cd0600442b5c9ec62698906fce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f36b072b11d40191824877fc40d5f21ac47778cd0600442b5c9ec62698906fce","first_computed_at":"2026-05-18T01:25:09.271493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:09.271493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O6uv3S07LFG7ad4WST3wc+HhPZKnwPIgyN5yfc/Pvu4IWGLCNI388bfx7WmIgSbl55yn0TJL2iX3qNnxwlcCBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:09.272171Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.01641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53ed574bfcf535af41140bfcd972e4fefee1ba19c06ea8d6ac684425da3e2a4a","sha256:821c8a035cb31775f3d9b1d634436d61df6fb8967cb2f036cbee8772428c8768"],"state_sha256":"34f8e9abbcbc96f25c8f663e936f9d1d9c656ad216605373d507d4fff95a503b"}