{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:56K3JH54UNX4KPBCQQSJJMQWGN","short_pith_number":"pith:56K3JH54","canonical_record":{"source":{"id":"1911.06154","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T02:09:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bb6f0912748fae4bb875493a24c84825a52f1148914ff56e7c20c8a5337ab9c8","abstract_canon_sha256":"59a37a1f347f7bef76b46f7f12d4bb2d5bd5ce87bbe842f6b56c078c0e943a97"},"schema_version":"1.0"},"canonical_sha256":"ef95b49fbca36fc53c22842494b2163375bca2a5e8b07f03221f68ce21b79905","source":{"kind":"arxiv","id":"1911.06154","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06154","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06154v2","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06154","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"56K3JH54UNX4","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"56K3JH54UNX4KPBC","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"56K3JH54","created_at":"2026-07-05T01:41:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:56K3JH54UNX4KPBCQQSJJMQWGN","target":"record","payload":{"canonical_record":{"source":{"id":"1911.06154","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T02:09:11Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bb6f0912748fae4bb875493a24c84825a52f1148914ff56e7c20c8a5337ab9c8","abstract_canon_sha256":"59a37a1f347f7bef76b46f7f12d4bb2d5bd5ce87bbe842f6b56c078c0e943a97"},"schema_version":"1.0"},"canonical_sha256":"ef95b49fbca36fc53c22842494b2163375bca2a5e8b07f03221f68ce21b79905","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:49.769870Z","signature_b64":"hKPStw7BiHzmiuCiBQjDiNQvlQb8kGQTbaTWg2ytIE3MByCjaRttTu8VoGjMgP0N38jyb4qmneW05Zjo0sTKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef95b49fbca36fc53c22842494b2163375bca2a5e8b07f03221f68ce21b79905","last_reissued_at":"2026-07-05T01:41:49.769335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:49.769335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.06154","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JTQ8B26wXcN/KKZA1+x0bMZBvBLEvBg1fxftsmlMJbeQu2Ydxc3fuJ+AwjXf/pSgRA12QpZlcW5MQmHTvby8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:59:54.649157Z"},"content_sha256":"76f9867d41c37e344c37ea91f00b9d6ea91eefd4d3118d787a05d0b818fdfc4e","schema_version":"1.0","event_id":"sha256:76f9867d41c37e344c37ea91f00b9d6ea91eefd4d3118d787a05d0b818fdfc4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:56K3JH54UNX4KPBCQQSJJMQWGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Francisco Guzman, Philipp Koehn, Vishrav Chaudhary","submitted_at":"2019-11-10T02:09:11Z","abstract_excerpt":"Cross-lingual document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. In this paper, we exploit the signals embedded in URLs to label web documents at scale with an average precision of 94.5% across different language pairs. We mine sixty-eight snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other. We release a new web dataset consisting of over 392 million URL pairs from Common Crawl covering documents in 8144 language pairs of which 137 pairs include Engli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06154","kind":"arxiv","version":2},"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/1911.06154/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":"2026-07-05T01:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1L4iWIGYqSaAoAz76w7r5FZNrpKW2H8e2k6656dbH8p4dGaGZoR014HCK2tA7V+KdQ1bBu3WJ59oPVDnY9wAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T23:59:54.650121Z"},"content_sha256":"9af825472e1a0b4ae1a30e829a85ca6462ccc608339459bf24f6cd6ae9c4d1e0","schema_version":"1.0","event_id":"sha256:9af825472e1a0b4ae1a30e829a85ca6462ccc608339459bf24f6cd6ae9c4d1e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/56K3JH54UNX4KPBCQQSJJMQWGN/bundle.json","state_url":"https://pith.science/pith/56K3JH54UNX4KPBCQQSJJMQWGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/56K3JH54UNX4KPBCQQSJJMQWGN/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":"2026-08-18T23:59:54Z","links":{"resolver":"https://pith.science/pith/56K3JH54UNX4KPBCQQSJJMQWGN","bundle":"https://pith.science/pith/56K3JH54UNX4KPBCQQSJJMQWGN/bundle.json","state":"https://pith.science/pith/56K3JH54UNX4KPBCQQSJJMQWGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/56K3JH54UNX4KPBCQQSJJMQWGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:56K3JH54UNX4KPBCQQSJJMQWGN","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":"59a37a1f347f7bef76b46f7f12d4bb2d5bd5ce87bbe842f6b56c078c0e943a97","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T02:09:11Z","title_canon_sha256":"bb6f0912748fae4bb875493a24c84825a52f1148914ff56e7c20c8a5337ab9c8"},"schema_version":"1.0","source":{"id":"1911.06154","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06154","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06154v2","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06154","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"56K3JH54UNX4","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"56K3JH54UNX4KPBC","created_at":"2026-07-05T01:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"56K3JH54","created_at":"2026-07-05T01:41:49Z"}],"graph_snapshots":[{"event_id":"sha256:9af825472e1a0b4ae1a30e829a85ca6462ccc608339459bf24f6cd6ae9c4d1e0","target":"graph","created_at":"2026-07-05T01:41:49Z","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/1911.06154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual document alignment aims to identify pairs of documents in two distinct languages that are of comparable content or translations of each other. In this paper, we exploit the signals embedded in URLs to label web documents at scale with an average precision of 94.5% across different language pairs. We mine sixty-eight snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other. We release a new web dataset consisting of over 392 million URL pairs from Common Crawl covering documents in 8144 language pairs of which 137 pairs include Engli","authors_text":"Ahmed El-Kishky, Francisco Guzman, Philipp Koehn, Vishrav Chaudhary","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T02:09:11Z","title":"CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06154","kind":"arxiv","version":2},"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":"sha256:76f9867d41c37e344c37ea91f00b9d6ea91eefd4d3118d787a05d0b818fdfc4e","target":"record","created_at":"2026-07-05T01:41:49Z","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":"59a37a1f347f7bef76b46f7f12d4bb2d5bd5ce87bbe842f6b56c078c0e943a97","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T02:09:11Z","title_canon_sha256":"bb6f0912748fae4bb875493a24c84825a52f1148914ff56e7c20c8a5337ab9c8"},"schema_version":"1.0","source":{"id":"1911.06154","kind":"arxiv","version":2}},"canonical_sha256":"ef95b49fbca36fc53c22842494b2163375bca2a5e8b07f03221f68ce21b79905","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef95b49fbca36fc53c22842494b2163375bca2a5e8b07f03221f68ce21b79905","first_computed_at":"2026-07-05T01:41:49.769335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:49.769335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hKPStw7BiHzmiuCiBQjDiNQvlQb8kGQTbaTWg2ytIE3MByCjaRttTu8VoGjMgP0N38jyb4qmneW05Zjo0sTKBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:49.769870Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.06154","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76f9867d41c37e344c37ea91f00b9d6ea91eefd4d3118d787a05d0b818fdfc4e","sha256:9af825472e1a0b4ae1a30e829a85ca6462ccc608339459bf24f6cd6ae9c4d1e0"],"state_sha256":"b8e26ca983f23db853e8b9d55196323710a47aac735f23f397426de96f9a4f7a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aW/Fs39tY5AKN6Xoleeo9HU4yH8x0Ho0YeQoZK0Nlz6ZcX0JkxZaaSHpXD8vIIM5S2CE3hzqv+pOYWTMuFW7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T23:59:54.655575Z","bundle_sha256":"ab43fe2707be7457ebbdd47d6beddf96a154c433a32837c02a0b045c72796cf8"}}