{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6XQBCO5KR6BIU2FYRNTILGQ74F","short_pith_number":"pith:6XQBCO5K","canonical_record":{"source":{"id":"1509.08639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T08:44:14Z","cross_cats_sorted":["cs.AI","cs.DS"],"title_canon_sha256":"b1b8c1944bc6c3ab858820c2c2b3c9850e854aaa0589ad40bb1516bbad4e47fa","abstract_canon_sha256":"f382424c16601c1410fc108fdfdfbbca80b79c697dbaa66f637f5622f24dca7a"},"schema_version":"1.0"},"canonical_sha256":"f5e0113baa8f828a68b88b66859a1fe17c01310d9b3014b6e9e6d40eda79bf1e","source":{"kind":"arxiv","id":"1509.08639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.08639","created_at":"2026-05-18T01:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"1509.08639v1","created_at":"2026-05-18T01:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.08639","created_at":"2026-05-18T01:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"6XQBCO5KR6BI","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6XQBCO5KR6BIU2FY","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6XQBCO5K","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6XQBCO5KR6BIU2FYRNTILGQ74F","target":"record","payload":{"canonical_record":{"source":{"id":"1509.08639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T08:44:14Z","cross_cats_sorted":["cs.AI","cs.DS"],"title_canon_sha256":"b1b8c1944bc6c3ab858820c2c2b3c9850e854aaa0589ad40bb1516bbad4e47fa","abstract_canon_sha256":"f382424c16601c1410fc108fdfdfbbca80b79c697dbaa66f637f5622f24dca7a"},"schema_version":"1.0"},"canonical_sha256":"f5e0113baa8f828a68b88b66859a1fe17c01310d9b3014b6e9e6d40eda79bf1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:31:47.418007Z","signature_b64":"FCUd99mLsB9Oc2YacanQw8uBpNncxIJX0Pxz54JQdSFW+SkPu7U6L4/BikTDuxOBMcaz0lQgiL6m0QLCh2JeAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e0113baa8f828a68b88b66859a1fe17c01310d9b3014b6e9e6d40eda79bf1e","last_reissued_at":"2026-05-18T01:31:47.417569Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:31:47.417569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.08639","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":"2026-05-18T01:31:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t63OyQPWS7RYJWMAME2hdYWrRNFXEA3SR5gSUWYQjAKwEo39CxYId2cQ6QfM1oNo6GTsbI8JqMxkaqvoMeebDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:34:00.808411Z"},"content_sha256":"2f971c1b23a3435818c6f10555652947e3889e213793df07be334e88f437dba6","schema_version":"1.0","event_id":"sha256:2f971c1b23a3435818c6f10555652947e3889e213793df07be334e88f437dba6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6XQBCO5KR6BIU2FYRNTILGQ74F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tuned and GPU-accelerated parallel data mining from comparable corpora","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS"],"primary_cat":"cs.CL","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","submitted_at":"2015-09-29T08:44:14Z","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 has a very limited availability especially for some languages and very narrow text domains. Is this research we present our improvements to Yalign mining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.08639","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":"2026-05-18T01:31:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQYG11KWOwKMDd5eq1tcURsZWpJv0fXQcZkK6woCl+sxsfSOlDgEUK9N1gbLN8KQpfQCZJd/TUNUBZrKFUNNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:34:00.809075Z"},"content_sha256":"c48059e77f066e345d56aaed4dbee050f6090345596fe28371ebb8829a6753d6","schema_version":"1.0","event_id":"sha256:c48059e77f066e345d56aaed4dbee050f6090345596fe28371ebb8829a6753d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XQBCO5KR6BIU2FYRNTILGQ74F/bundle.json","state_url":"https://pith.science/pith/6XQBCO5KR6BIU2FYRNTILGQ74F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XQBCO5KR6BIU2FYRNTILGQ74F/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":"2026-05-25T22:34:00Z","links":{"resolver":"https://pith.science/pith/6XQBCO5KR6BIU2FYRNTILGQ74F","bundle":"https://pith.science/pith/6XQBCO5KR6BIU2FYRNTILGQ74F/bundle.json","state":"https://pith.science/pith/6XQBCO5KR6BIU2FYRNTILGQ74F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XQBCO5KR6BIU2FYRNTILGQ74F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6XQBCO5KR6BIU2FYRNTILGQ74F","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":"f382424c16601c1410fc108fdfdfbbca80b79c697dbaa66f637f5622f24dca7a","cross_cats_sorted":["cs.AI","cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T08:44:14Z","title_canon_sha256":"b1b8c1944bc6c3ab858820c2c2b3c9850e854aaa0589ad40bb1516bbad4e47fa"},"schema_version":"1.0","source":{"id":"1509.08639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.08639","created_at":"2026-05-18T01:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"1509.08639v1","created_at":"2026-05-18T01:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.08639","created_at":"2026-05-18T01:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"6XQBCO5KR6BI","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6XQBCO5KR6BIU2FY","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6XQBCO5K","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:c48059e77f066e345d56aaed4dbee050f6090345596fe28371ebb8829a6753d6","target":"graph","created_at":"2026-05-18T01:31:47Z","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 has a very limited availability especially for some languages and very narrow text domains. Is this research we present our improvements to Yalign mining","authors_text":"Krzysztof Marasek, Krzysztof Wo{\\l}k","cross_cats":["cs.AI","cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T08:44:14Z","title":"Tuned and GPU-accelerated parallel data mining from comparable corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.08639","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":"sha256:2f971c1b23a3435818c6f10555652947e3889e213793df07be334e88f437dba6","target":"record","created_at":"2026-05-18T01:31:47Z","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":"f382424c16601c1410fc108fdfdfbbca80b79c697dbaa66f637f5622f24dca7a","cross_cats_sorted":["cs.AI","cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-09-29T08:44:14Z","title_canon_sha256":"b1b8c1944bc6c3ab858820c2c2b3c9850e854aaa0589ad40bb1516bbad4e47fa"},"schema_version":"1.0","source":{"id":"1509.08639","kind":"arxiv","version":1}},"canonical_sha256":"f5e0113baa8f828a68b88b66859a1fe17c01310d9b3014b6e9e6d40eda79bf1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e0113baa8f828a68b88b66859a1fe17c01310d9b3014b6e9e6d40eda79bf1e","first_computed_at":"2026-05-18T01:31:47.417569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:31:47.417569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FCUd99mLsB9Oc2YacanQw8uBpNncxIJX0Pxz54JQdSFW+SkPu7U6L4/BikTDuxOBMcaz0lQgiL6m0QLCh2JeAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:31:47.418007Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.08639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f971c1b23a3435818c6f10555652947e3889e213793df07be334e88f437dba6","sha256:c48059e77f066e345d56aaed4dbee050f6090345596fe28371ebb8829a6753d6"],"state_sha256":"4b04c1d04667d41bfb6a315476d1f5bf1e71ce163518464930cbb35a349f05cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qCzHGXT77XBKo5xfHFiNaIUvUcHtEjwnRaj3Vnb9J0PpFZNREczU8Ljes5e1+hd+Op44xg8tvgWOBqthPeAwAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:34:00.812934Z","bundle_sha256":"9590e0aedbcc63b5f5cc69e9d2095007d2c19c1833977d8ee37559c69ef78073"}}