{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Q7QN5Z4C3MHPTYTG6UJ7YH3L5J","short_pith_number":"pith:Q7QN5Z4C","canonical_record":{"source":{"id":"2007.03006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-06T18:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"39df020c19023813f83f39596069f994864f907739a49a16cf6136245ec341bb","abstract_canon_sha256":"fe8bd98e629830e154829aa44c16bf4a380f2a76183d48dd491e6a405832e817"},"schema_version":"1.0"},"canonical_sha256":"87e0dee782db0ef9e266f513fc1f6bea5264061aad291b5d64d363736d12b21a","source":{"kind":"arxiv","id":"2007.03006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03006","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03006v1","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03006","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"Q7QN5Z4C3MHP","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"Q7QN5Z4C3MHPTYTG","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"Q7QN5Z4C","created_at":"2026-07-05T01:16:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Q7QN5Z4C3MHPTYTG6UJ7YH3L5J","target":"record","payload":{"canonical_record":{"source":{"id":"2007.03006","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-06T18:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"39df020c19023813f83f39596069f994864f907739a49a16cf6136245ec341bb","abstract_canon_sha256":"fe8bd98e629830e154829aa44c16bf4a380f2a76183d48dd491e6a405832e817"},"schema_version":"1.0"},"canonical_sha256":"87e0dee782db0ef9e266f513fc1f6bea5264061aad291b5d64d363736d12b21a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:58.763303Z","signature_b64":"k4WLLpRWHtBMBlEupEi9brRHtinGrHyelqd092bLI1onmKV4+45GM7j0F9ifXzcdwm343w3eKukSrLY2liZ+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87e0dee782db0ef9e266f513fc1f6bea5264061aad291b5d64d363736d12b21a","last_reissued_at":"2026-07-05T01:16:58.762882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:58.762882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.03006","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":"2026-07-05T01:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bd2YFM9DsXEVoR0Ckm72yRGx7RcaUsZicy/VkmGL2MqwGF/tLQYjTJySaDpnsPjsiLAXBlDGbkJ3B2ze9VkdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:49:42.097742Z"},"content_sha256":"a7d52fc69cfca6862de29d09661db2fb1aaa79ad5c198564a666110ea929dd1c","schema_version":"1.0","event_id":"sha256:a7d52fc69cfca6862de29d09661db2fb1aaa79ad5c198564a666110ea929dd1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Q7QN5Z4C3MHPTYTG6UJ7YH3L5J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Martin Popel, Ondrej Bojar, Tom Kocmi","submitted_at":"2020-07-06T18:48:11Z","abstract_excerpt":"We present a new release of the Czech-English parallel corpus CzEng 2.0 consisting of over 2 billion words (2 \"gigawords\") in each language. The corpus contains document-level information and is filtered with several techniques to lower the amount of noise. In addition to the data in the previous version of CzEng, it contains new authentic and also high-quality synthetic parallel data. CzEng is freely available for research and educational purposes."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03006","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2007.03006/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T01:16:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLqndIgFPscG/fve44D6gjuBD8wY34sDg4socJpIEK09y8VwLPhiRR+UaJcvTrGVUsonApPM8r7W4TqoUIxAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:49:42.099999Z"},"content_sha256":"8a9b1df39ab55455f398562c159c5e288df46bdc56c2c042ebf236460f1c885a","schema_version":"1.0","event_id":"sha256:8a9b1df39ab55455f398562c159c5e288df46bdc56c2c042ebf236460f1c885a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J/bundle.json","state_url":"https://pith.science/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J/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":"2026-08-18T15:49:42Z","links":{"resolver":"https://pith.science/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J","bundle":"https://pith.science/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J/bundle.json","state":"https://pith.science/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q7QN5Z4C3MHPTYTG6UJ7YH3L5J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Q7QN5Z4C3MHPTYTG6UJ7YH3L5J","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":"fe8bd98e629830e154829aa44c16bf4a380f2a76183d48dd491e6a405832e817","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-06T18:48:11Z","title_canon_sha256":"39df020c19023813f83f39596069f994864f907739a49a16cf6136245ec341bb"},"schema_version":"1.0","source":{"id":"2007.03006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.03006","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"arxiv_version","alias_value":"2007.03006v1","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03006","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"pith_short_12","alias_value":"Q7QN5Z4C3MHP","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"pith_short_16","alias_value":"Q7QN5Z4C3MHPTYTG","created_at":"2026-07-05T01:16:58Z"},{"alias_kind":"pith_short_8","alias_value":"Q7QN5Z4C","created_at":"2026-07-05T01:16:58Z"}],"graph_snapshots":[{"event_id":"sha256:8a9b1df39ab55455f398562c159c5e288df46bdc56c2c042ebf236460f1c885a","target":"graph","created_at":"2026-07-05T01:16:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2007.03006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new release of the Czech-English parallel corpus CzEng 2.0 consisting of over 2 billion words (2 \"gigawords\") in each language. The corpus contains document-level information and is filtered with several techniques to lower the amount of noise. In addition to the data in the previous version of CzEng, it contains new authentic and also high-quality synthetic parallel data. CzEng is freely available for research and educational purposes.","authors_text":"Martin Popel, Ondrej Bojar, Tom Kocmi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-06T18:48:11Z","title":"Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03006","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:a7d52fc69cfca6862de29d09661db2fb1aaa79ad5c198564a666110ea929dd1c","target":"record","created_at":"2026-07-05T01:16:58Z","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":"fe8bd98e629830e154829aa44c16bf4a380f2a76183d48dd491e6a405832e817","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-06T18:48:11Z","title_canon_sha256":"39df020c19023813f83f39596069f994864f907739a49a16cf6136245ec341bb"},"schema_version":"1.0","source":{"id":"2007.03006","kind":"arxiv","version":1}},"canonical_sha256":"87e0dee782db0ef9e266f513fc1f6bea5264061aad291b5d64d363736d12b21a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87e0dee782db0ef9e266f513fc1f6bea5264061aad291b5d64d363736d12b21a","first_computed_at":"2026-07-05T01:16:58.762882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:58.762882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4WLLpRWHtBMBlEupEi9brRHtinGrHyelqd092bLI1onmKV4+45GM7j0F9ifXzcdwm343w3eKukSrLY2liZ+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:58.763303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.03006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7d52fc69cfca6862de29d09661db2fb1aaa79ad5c198564a666110ea929dd1c","sha256:8a9b1df39ab55455f398562c159c5e288df46bdc56c2c042ebf236460f1c885a"],"state_sha256":"b21d930466304f6f58f66532361aeaf79137b9e33cc3b0b98f3854986190e026"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FPr2h64ToV1Gwd+RQpUyle2o5dN8kJyCeLzHygSmjK9aQHUXpCWJTKz1aY34Hek8KmV3TA91BTnpjM1S7kXNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:49:42.107043Z","bundle_sha256":"662dca2fc7c582a4db377e34e539dbb72979e77075d1ee685d5bcdfb0a811d2d"}}