{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ATBU2NV676TGCTWHMJ6XQ4MIRI","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":"96b93958c24b76f934a5d7577107e7d4994c1f745de39cecd5b241d1d0f53d5e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T08:56:13Z","title_canon_sha256":"9b616d1def0f2c362f38c9069cc682c722b62e468bb31bb27722d1f0f4c79e32"},"schema_version":"1.0","source":{"id":"2401.05749","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05749","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05749v2","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05749","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_12","alias_value":"ATBU2NV676TG","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_16","alias_value":"ATBU2NV676TGCTWH","created_at":"2026-07-05T08:28:04Z"},{"alias_kind":"pith_short_8","alias_value":"ATBU2NV6","created_at":"2026-07-05T08:28:04Z"}],"graph_snapshots":[{"event_id":"sha256:2e6e85c9731dd840b634762c6506b777837b3fbc4db562b62ad5285fbf9144d5","target":"graph","created_at":"2026-07-05T08:28:04Z","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/2401.05749/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that content on the web is often translated into many languages, and the low quality of these multi-way translations indicates they were likely created using Machine Translation (MT). Multi-way parallel, machine generated content not only dominates the translations in lower resource languages; it also constitutes a large fraction of the total web content in those languages. We also find evidence of a selection bias in the type of content which is translated into many languages, consistent with low quality English content being translated en masse into many lower resource languages, via","authors_text":"Brian Thompson, Marcello Federico, Mehak Preet Dhaliwal, Peter Frisch, Tobias Domhan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T08:56:13Z","title":"A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05749","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":"sha256:4ed53ad8f31ab6394dae6fcc8733a2a212c8cb626195fbf092ddb4262ca94089","target":"record","created_at":"2026-07-05T08:28:04Z","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":"96b93958c24b76f934a5d7577107e7d4994c1f745de39cecd5b241d1d0f53d5e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T08:56:13Z","title_canon_sha256":"9b616d1def0f2c362f38c9069cc682c722b62e468bb31bb27722d1f0f4c79e32"},"schema_version":"1.0","source":{"id":"2401.05749","kind":"arxiv","version":2}},"canonical_sha256":"04c34d36beffa6614ec7627d7871888a018958c2b8010cdcfc3a00da49d0ad60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04c34d36beffa6614ec7627d7871888a018958c2b8010cdcfc3a00da49d0ad60","first_computed_at":"2026-07-05T08:28:04.794268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:04.794268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sZOuYMHelLhTbNH9RJ/FPGnjB5uQv/PqrLmOkcqq1J3ZKvLi2l71zUJ597OQGmyUco2GSZBNJtZLrOjMGKudDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:04.794705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05749","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ed53ad8f31ab6394dae6fcc8733a2a212c8cb626195fbf092ddb4262ca94089","sha256:2e6e85c9731dd840b634762c6506b777837b3fbc4db562b62ad5285fbf9144d5"],"state_sha256":"e4a74845a830e7fc281e371c8c1dadb9b0dd7812f8139f375c514f47619adc3b"}