{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:74SKHVPQCDG2DJKF545NAUOJIE","short_pith_number":"pith:74SKHVPQ","canonical_record":{"source":{"id":"2205.03983","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-09T00:24:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4589c58a25b4651b3301773ad730a54b587f99ddff32d86b6002a737f2040c85","abstract_canon_sha256":"22819a84950f0f87d1a63f022cbc79547d4ff115184b6353fd48a683e5c7c5ad"},"schema_version":"1.0"},"canonical_sha256":"ff24a3d5f010cda1a545ef3ad051c94110d328df4917d82b771dfbc56510a923","source":{"kind":"arxiv","id":"2205.03983","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03983","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03983v3","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03983","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"74SKHVPQCDG2","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_16","alias_value":"74SKHVPQCDG2DJKF","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_8","alias_value":"74SKHVPQ","created_at":"2026-07-05T04:38:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:74SKHVPQCDG2DJKF545NAUOJIE","target":"record","payload":{"canonical_record":{"source":{"id":"2205.03983","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-09T00:24:13Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4589c58a25b4651b3301773ad730a54b587f99ddff32d86b6002a737f2040c85","abstract_canon_sha256":"22819a84950f0f87d1a63f022cbc79547d4ff115184b6353fd48a683e5c7c5ad"},"schema_version":"1.0"},"canonical_sha256":"ff24a3d5f010cda1a545ef3ad051c94110d328df4917d82b771dfbc56510a923","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:14.976275Z","signature_b64":"PsjhEqvQUKw123q6n0WsZYJAszGvk7TaJFCcJke1Ty7pxii1LtAku5b87YiZeqDzXhWH+HpBpMmlzrMVU70uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff24a3d5f010cda1a545ef3ad051c94110d328df4917d82b771dfbc56510a923","last_reissued_at":"2026-07-05T04:38:14.975812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:14.975812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.03983","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmVtwGG5bMSSxi7a3xf7yvDhoZWs+4PgfkiO1FWK9OGz2t62OZibA9s5Ih5LWhFKPevJJAtpP8UYysS0bk8hDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:27:56.863782Z"},"content_sha256":"49321bb1d8259d77d2fe5e7871f73543a5956bfb451458f6d85d42282792e519","schema_version":"1.0","event_id":"sha256:49321bb1d8259d77d2fe5e7871f73543a5956bfb451458f6d85d42282792e519"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:74SKHVPQCDG2DJKF545NAUOJIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Machine Translation Systems for the Next Thousand Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Alexander Gutkin, Ankur Bapna, Apurva Shah, Daan van Esch, Isaac Caswell, Jason Riesa, Julia Kreutzer, Klaus Macherey, Macduff Hughes, Maxim Krikun, Mengmeng Niu, Mia Xu Chen, Orhan Firat, Pallavi Baljekar, Pidong Wang, Theresa Breiner, Vera Axelrod, Wolfgang Macherey, Xavier Garcia, Yanping Huang, Yonghui Wu, Yuan Cao, Zhifeng Chen","submitted_at":"2022-05-09T00:24:13Z","abstract_excerpt":"In this paper we share findings from our effort to build practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results in three research domains: (i) Building clean, web-mined datasets for 1500+ languages by leveraging semi-supervised pre-training for language identification and developing data-driven filtering techniques; (ii) Developing practical MT models for under-served languages by leveraging massively multilingual models trained with supervised parallel data for over 100 high-resource languages and monolingual datasets for an a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03983","kind":"arxiv","version":3},"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/2205.03983/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":"2026-07-05T04:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cfy5iguNiQ6AyaPOPimEP33mwZoa7oyltTw5REfyOhuKzAK9kBOHafpOULIK7LjSRQueo7oo+mg3mpZvG0o/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:27:56.864306Z"},"content_sha256":"7f8b2eead7050158a1e9506ee5373d649ef2cdf1ab3eda5fb474df2032dc33d6","schema_version":"1.0","event_id":"sha256:7f8b2eead7050158a1e9506ee5373d649ef2cdf1ab3eda5fb474df2032dc33d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74SKHVPQCDG2DJKF545NAUOJIE/bundle.json","state_url":"https://pith.science/pith/74SKHVPQCDG2DJKF545NAUOJIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74SKHVPQCDG2DJKF545NAUOJIE/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":"2026-08-11T15:27:56Z","links":{"resolver":"https://pith.science/pith/74SKHVPQCDG2DJKF545NAUOJIE","bundle":"https://pith.science/pith/74SKHVPQCDG2DJKF545NAUOJIE/bundle.json","state":"https://pith.science/pith/74SKHVPQCDG2DJKF545NAUOJIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74SKHVPQCDG2DJKF545NAUOJIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:74SKHVPQCDG2DJKF545NAUOJIE","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":"22819a84950f0f87d1a63f022cbc79547d4ff115184b6353fd48a683e5c7c5ad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-09T00:24:13Z","title_canon_sha256":"4589c58a25b4651b3301773ad730a54b587f99ddff32d86b6002a737f2040c85"},"schema_version":"1.0","source":{"id":"2205.03983","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03983","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03983v3","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03983","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"74SKHVPQCDG2","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_16","alias_value":"74SKHVPQCDG2DJKF","created_at":"2026-07-05T04:38:14Z"},{"alias_kind":"pith_short_8","alias_value":"74SKHVPQ","created_at":"2026-07-05T04:38:14Z"}],"graph_snapshots":[{"event_id":"sha256:7f8b2eead7050158a1e9506ee5373d649ef2cdf1ab3eda5fb474df2032dc33d6","target":"graph","created_at":"2026-07-05T04:38:14Z","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/2205.03983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we share findings from our effort to build practical machine translation (MT) systems capable of translating across over one thousand languages. We describe results in three research domains: (i) Building clean, web-mined datasets for 1500+ languages by leveraging semi-supervised pre-training for language identification and developing data-driven filtering techniques; (ii) Developing practical MT models for under-served languages by leveraging massively multilingual models trained with supervised parallel data for over 100 high-resource languages and monolingual datasets for an a","authors_text":"Aditya Siddhant, Alexander Gutkin, Ankur Bapna, Apurva Shah, Daan van Esch, Isaac Caswell, Jason Riesa, Julia Kreutzer, Klaus Macherey, Macduff Hughes, Maxim Krikun, Mengmeng Niu, Mia Xu Chen, Orhan Firat, Pallavi Baljekar, Pidong Wang, Theresa Breiner, Vera Axelrod, Wolfgang Macherey, Xavier Garcia, Yanping Huang, Yonghui Wu, Yuan Cao, Zhifeng Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-09T00:24:13Z","title":"Building Machine Translation Systems for the Next Thousand Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03983","kind":"arxiv","version":3},"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":"sha256:49321bb1d8259d77d2fe5e7871f73543a5956bfb451458f6d85d42282792e519","target":"record","created_at":"2026-07-05T04:38:14Z","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":"22819a84950f0f87d1a63f022cbc79547d4ff115184b6353fd48a683e5c7c5ad","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-09T00:24:13Z","title_canon_sha256":"4589c58a25b4651b3301773ad730a54b587f99ddff32d86b6002a737f2040c85"},"schema_version":"1.0","source":{"id":"2205.03983","kind":"arxiv","version":3}},"canonical_sha256":"ff24a3d5f010cda1a545ef3ad051c94110d328df4917d82b771dfbc56510a923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff24a3d5f010cda1a545ef3ad051c94110d328df4917d82b771dfbc56510a923","first_computed_at":"2026-07-05T04:38:14.975812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:14.975812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PsjhEqvQUKw123q6n0WsZYJAszGvk7TaJFCcJke1Ty7pxii1LtAku5b87YiZeqDzXhWH+HpBpMmlzrMVU70uDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:14.976275Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.03983","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49321bb1d8259d77d2fe5e7871f73543a5956bfb451458f6d85d42282792e519","sha256:7f8b2eead7050158a1e9506ee5373d649ef2cdf1ab3eda5fb474df2032dc33d6"],"state_sha256":"a168d9c964745940943e25e8a802bfe86df6d1783b1b99e30dd1de6ae77dbc4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pzR2GNrgQeiziyV3ur+y9EDWnaT6ssQwyQChuWpuHz9VF/aemAB0A1IVOUWht7v7NPw7lh/fe2n2OOrDSc8uBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:27:56.868939Z","bundle_sha256":"b9b362bb46e171c07ebb40054acc4fed70dec9e9ed567b6286cfdbd6bffd2b68"}}