{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5DYJDXJYPPHPKX6IQEWS7BBATK","short_pith_number":"pith:5DYJDXJY","canonical_record":{"source":{"id":"1804.10413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-27T09:33:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb261c8b2f83aa07feb03c505aef3c9100f9f966f9fe8eed1f35fb1a0023fc47","abstract_canon_sha256":"dac2160096da87e79ab5567001c327bc3629a146841b877ceff0b993a3b66bb8"},"schema_version":"1.0"},"canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","source":{"kind":"arxiv","id":"1804.10413","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10413","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10413v1","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10413","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"5DYJDXJYPPHP","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5DYJDXJYPPHPKX6I","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5DYJDXJY","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5DYJDXJYPPHPKX6IQEWS7BBATK","target":"record","payload":{"canonical_record":{"source":{"id":"1804.10413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-27T09:33:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb261c8b2f83aa07feb03c505aef3c9100f9f966f9fe8eed1f35fb1a0023fc47","abstract_canon_sha256":"dac2160096da87e79ab5567001c327bc3629a146841b877ceff0b993a3b66bb8"},"schema_version":"1.0"},"canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:20.856096Z","signature_b64":"TI8wdz+QVfEfAK4FwaJq1URwvY04k3m0nd30hkXv8fSPyzajkL3RdoTqww9FrBjH1kb/g6ViBtnOcjkCc6l3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","last_reissued_at":"2026-05-18T00:17:20.855392Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:20.855392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.10413","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":"2026-05-18T00:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iSOnc2PPdVLpA/5ZZurUuohwtQ5vqhVy9IllkJqpNPI4GQsvIceAhKp4ptRD4zij6gjAtUogr6xN+0oHe+CyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:28:09.120306Z"},"content_sha256":"f51098ed70c949882397d338e07cc65696d4a2738fd189df0838d9975b4364a0","schema_version":"1.0","event_id":"sha256:f51098ed70c949882397d338e07cc65696d4a2738fd189df0838d9975b4364a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5DYJDXJYPPHPKX6IQEWS7BBATK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting Parallel Paragraphs from Common Crawl","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Irena Holubov\\'a, Jakub K\\'udela, Ond\\v{r}ej Bojar","submitted_at":"2018-04-27T09:33:49Z","abstract_excerpt":"Most of the current methods for mining parallel texts from the web assume that web pages of web sites share same structure across languages. We believe that there still exists a non-negligible amount of parallel data spread across sources not satisfying this assumption. We propose an approach based on a combination of bivec (a bilingual extension of word2vec) and locality-sensitive hashing which allows us to efficiently identify pairs of parallel segments located anywhere on pages of a given web domain, regardless their structure. We validate our method on realigning segments from a large para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10413","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":"2026-05-18T00:17:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xdCc6m7YU3a3utztNTyZtAVjG6yvsa9yT+uBflCPrHyLP3zebRmNyLC5Fupg18N7gMBjFtmAmamrkYTFJuTyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:28:09.120964Z"},"content_sha256":"7fd0184be50174523f0e3bab079a2321888a278f7e20f671fbbc6515b9ee1f2e","schema_version":"1.0","event_id":"sha256:7fd0184be50174523f0e3bab079a2321888a278f7e20f671fbbc6515b9ee1f2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/bundle.json","state_url":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/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":"2026-06-06T16:28:09Z","links":{"resolver":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK","bundle":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/bundle.json","state":"https://pith.science/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DYJDXJYPPHPKX6IQEWS7BBATK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5DYJDXJYPPHPKX6IQEWS7BBATK","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":"dac2160096da87e79ab5567001c327bc3629a146841b877ceff0b993a3b66bb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-27T09:33:49Z","title_canon_sha256":"fb261c8b2f83aa07feb03c505aef3c9100f9f966f9fe8eed1f35fb1a0023fc47"},"schema_version":"1.0","source":{"id":"1804.10413","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10413","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10413v1","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10413","created_at":"2026-05-18T00:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"5DYJDXJYPPHP","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5DYJDXJYPPHPKX6I","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5DYJDXJY","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:7fd0184be50174523f0e3bab079a2321888a278f7e20f671fbbc6515b9ee1f2e","target":"graph","created_at":"2026-05-18T00:17:20Z","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":"Most of the current methods for mining parallel texts from the web assume that web pages of web sites share same structure across languages. We believe that there still exists a non-negligible amount of parallel data spread across sources not satisfying this assumption. We propose an approach based on a combination of bivec (a bilingual extension of word2vec) and locality-sensitive hashing which allows us to efficiently identify pairs of parallel segments located anywhere on pages of a given web domain, regardless their structure. We validate our method on realigning segments from a large para","authors_text":"Irena Holubov\\'a, Jakub K\\'udela, Ond\\v{r}ej Bojar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-27T09:33:49Z","title":"Extracting Parallel Paragraphs from Common Crawl"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10413","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:f51098ed70c949882397d338e07cc65696d4a2738fd189df0838d9975b4364a0","target":"record","created_at":"2026-05-18T00:17:20Z","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":"dac2160096da87e79ab5567001c327bc3629a146841b877ceff0b993a3b66bb8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-27T09:33:49Z","title_canon_sha256":"fb261c8b2f83aa07feb03c505aef3c9100f9f966f9fe8eed1f35fb1a0023fc47"},"schema_version":"1.0","source":{"id":"1804.10413","kind":"arxiv","version":1}},"canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8f091dd387bcef55fc8812d2f84209a9b117f5c8ff5ba4ff514bf4694b08e07","first_computed_at":"2026-05-18T00:17:20.855392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:20.855392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TI8wdz+QVfEfAK4FwaJq1URwvY04k3m0nd30hkXv8fSPyzajkL3RdoTqww9FrBjH1kb/g6ViBtnOcjkCc6l3CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:20.856096Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.10413","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f51098ed70c949882397d338e07cc65696d4a2738fd189df0838d9975b4364a0","sha256:7fd0184be50174523f0e3bab079a2321888a278f7e20f671fbbc6515b9ee1f2e"],"state_sha256":"38ddc81792a329f120de7a8a1c59ebe96de06cf7d889cbd073293d04fbdf4af8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9SOV/QyMYMQer1ZvXWXj92LzfomHS2nxI6d20HQ0I99Qrte6nUGQ1cZ81zNmbUCMei79usklUADE3pPXQPH3DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T16:28:09.124703Z","bundle_sha256":"82c31420ac1d8217c5ec74e481ebc9b14656e2947cabd1a1d594fb5f61e7d5cb"}}