{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6NVQOKYR2QAZDASIO76EBVPSDL","short_pith_number":"pith:6NVQOKYR","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"},"canonical_sha256":"f36b072b11d40191824877fc40d5f21ac47778cd0600442b5c9ec62698906fce","source":{"kind":"arxiv","id":"1512.01641","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6NVQOKYR2QAZDASIO76EBVPSDL","target":"record","payload":{"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"},"canonical_sha256":"f36b072b11d40191824877fc40d5f21ac47778cd0600442b5c9ec62698906fce","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"},"source_kind":"arxiv","source_id":"1512.01641","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZmp/0HIpwXvNjmI2i80d3Q7B4HPqcMzZUVZfuf8LaW8wU1zi92yFrsRxoqzW2hrbFBmLOY3ZhssUU4HAen0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:55:06.904496Z"},"content_sha256":"53ed574bfcf535af41140bfcd972e4fefee1ba19c06ea8d6ac684425da3e2a4a","schema_version":"1.0","event_id":"sha256:53ed574bfcf535af41140bfcd972e4fefee1ba19c06ea8d6ac684425da3e2a4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6NVQOKYR2QAZDASIO76EBVPSDL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:25:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"13LziSr18jmuXZ/un3ekOP4nEqcOd9L6HI/zRVGna9J0QxmVFj3UEId4vv5Hb0WnEk0XeVvkuGsCuDYHyXaLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T10:55:06.904930Z"},"content_sha256":"821c8a035cb31775f3d9b1d634436d61df6fb8967cb2f036cbee8772428c8768","schema_version":"1.0","event_id":"sha256:821c8a035cb31775f3d9b1d634436d61df6fb8967cb2f036cbee8772428c8768"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/bundle.json","state_url":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6NVQOKYR2QAZDASIO76EBVPSDL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T10:55:06Z","links":{"resolver":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL","bundle":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/bundle.json","state":"https://pith.science/pith/6NVQOKYR2QAZDASIO76EBVPSDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6NVQOKYR2QAZDASIO76EBVPSDL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmtClZpn7KChq7AnYR2jI7hJn9GHzLw1SVGErPjJkdYiTVfp+ckoZxiUAbEoSselNzthWusD0lW/tXVDsnKoBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T10:55:06.908330Z","bundle_sha256":"d30b66e86a5b06f6d92f21de12182fb83a279ef4ef0c6868b01a532a0f0194e1"}}