{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GELEM4P75QO25RNSC67WFYBEH4","short_pith_number":"pith:GELEM4P7","canonical_record":{"source":{"id":"2104.00290","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T06:55:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8523b0f682ac53a4114b8002531812bdd26807c935fb79a22581f62f04bd3264","abstract_canon_sha256":"3a0d1b9cc51ba5ce03adebf9b0099cb19543d9f13892d6be712579cf8998c6f1"},"schema_version":"1.0"},"canonical_sha256":"31164671ffec1daec5b217bf62e0243f331f6b0c8ec7ea68082bd9c0ffd7e32d","source":{"kind":"arxiv","id":"2104.00290","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00290","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00290v2","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00290","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"GELEM4P75QO2","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"pith_short_16","alias_value":"GELEM4P75QO25RNS","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"pith_short_8","alias_value":"GELEM4P7","created_at":"2026-07-05T09:24:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GELEM4P75QO25RNSC67WFYBEH4","target":"record","payload":{"canonical_record":{"source":{"id":"2104.00290","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T06:55:12Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8523b0f682ac53a4114b8002531812bdd26807c935fb79a22581f62f04bd3264","abstract_canon_sha256":"3a0d1b9cc51ba5ce03adebf9b0099cb19543d9f13892d6be712579cf8998c6f1"},"schema_version":"1.0"},"canonical_sha256":"31164671ffec1daec5b217bf62e0243f331f6b0c8ec7ea68082bd9c0ffd7e32d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:14.281305Z","signature_b64":"GAlvf3qmPD+KH8/4LAeUjLq2tgSj6/rMIeYSqgCeZ4EJttzDpUVMyywQrlT16wBG0Gt6iy7U0ENSTp/hbDTgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31164671ffec1daec5b217bf62e0243f331f6b0c8ec7ea68082bd9c0ffd7e32d","last_reissued_at":"2026-07-05T09:24:14.280777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:14.280777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.00290","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":"2026-07-05T09:24:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R97gfB9B8BTH+pCnflg/LMpuJcdGp0k1ps9zmOxljJJe4CDEkvyOHlc/wnIcgEIpYnv6iuBHcWG4vDhHTvERAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:15:25.457876Z"},"content_sha256":"1e9da7e7f006a6788147ced3b94113b1578e5a86c427a4d789d6f1c48eae8131","schema_version":"1.0","event_id":"sha256:1e9da7e7f006a6788147ced3b94113b1578e5a86c427a4d789d6f1c48eae8131"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GELEM4P75QO25RNSC67WFYBEH4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chris A Mattmann, Jonathan May, Thamme Gowda, Zhao Zhang","submitted_at":"2021-04-01T06:55:12Z","abstract_excerpt":"While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models available for transfer to low resource languages. In this work, we present useful tools for machine translation research: MTData, NLCodec, and RTG. We demonstrate their usefulness by creating a multilingual neural machine translation model capable of translating from 500 source languages to English. We make this multilingual model readily downloadable and usa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00290","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/2104.00290/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":"2026-07-05T09:24:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UAvoqnpvFNvHcH4zqAdnT1w7c0HX9oEjxWoTNDJEPtswxKUhM2eYwhEIUAvpap9q66uwvAh3SapQN74hFxaXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:15:25.459050Z"},"content_sha256":"5d6b928515bb4366eb9e497558d9eb97e37d45010fd3a1fd75f395eae79d504e","schema_version":"1.0","event_id":"sha256:5d6b928515bb4366eb9e497558d9eb97e37d45010fd3a1fd75f395eae79d504e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GELEM4P75QO25RNSC67WFYBEH4/bundle.json","state_url":"https://pith.science/pith/GELEM4P75QO25RNSC67WFYBEH4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GELEM4P75QO25RNSC67WFYBEH4/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":"2026-08-05T15:15:25Z","links":{"resolver":"https://pith.science/pith/GELEM4P75QO25RNSC67WFYBEH4","bundle":"https://pith.science/pith/GELEM4P75QO25RNSC67WFYBEH4/bundle.json","state":"https://pith.science/pith/GELEM4P75QO25RNSC67WFYBEH4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GELEM4P75QO25RNSC67WFYBEH4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GELEM4P75QO25RNSC67WFYBEH4","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":"3a0d1b9cc51ba5ce03adebf9b0099cb19543d9f13892d6be712579cf8998c6f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T06:55:12Z","title_canon_sha256":"8523b0f682ac53a4114b8002531812bdd26807c935fb79a22581f62f04bd3264"},"schema_version":"1.0","source":{"id":"2104.00290","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00290","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00290v2","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00290","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"pith_short_12","alias_value":"GELEM4P75QO2","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"pith_short_16","alias_value":"GELEM4P75QO25RNS","created_at":"2026-07-05T09:24:14Z"},{"alias_kind":"pith_short_8","alias_value":"GELEM4P7","created_at":"2026-07-05T09:24:14Z"}],"graph_snapshots":[{"event_id":"sha256:5d6b928515bb4366eb9e497558d9eb97e37d45010fd3a1fd75f395eae79d504e","target":"graph","created_at":"2026-07-05T09:24:14Z","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/2104.00290/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While there are more than 7000 languages in the world, most translation research efforts have targeted a few high-resource languages. Commercial translation systems support only one hundred languages or fewer, and do not make these models available for transfer to low resource languages. In this work, we present useful tools for machine translation research: MTData, NLCodec, and RTG. We demonstrate their usefulness by creating a multilingual neural machine translation model capable of translating from 500 source languages to English. We make this multilingual model readily downloadable and usa","authors_text":"Chris A Mattmann, Jonathan May, Thamme Gowda, Zhao Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T06:55:12Z","title":"Many-to-English Machine Translation Tools, Data, and Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00290","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":"sha256:1e9da7e7f006a6788147ced3b94113b1578e5a86c427a4d789d6f1c48eae8131","target":"record","created_at":"2026-07-05T09:24:14Z","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":"3a0d1b9cc51ba5ce03adebf9b0099cb19543d9f13892d6be712579cf8998c6f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T06:55:12Z","title_canon_sha256":"8523b0f682ac53a4114b8002531812bdd26807c935fb79a22581f62f04bd3264"},"schema_version":"1.0","source":{"id":"2104.00290","kind":"arxiv","version":2}},"canonical_sha256":"31164671ffec1daec5b217bf62e0243f331f6b0c8ec7ea68082bd9c0ffd7e32d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31164671ffec1daec5b217bf62e0243f331f6b0c8ec7ea68082bd9c0ffd7e32d","first_computed_at":"2026-07-05T09:24:14.280777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:14.280777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GAlvf3qmPD+KH8/4LAeUjLq2tgSj6/rMIeYSqgCeZ4EJttzDpUVMyywQrlT16wBG0Gt6iy7U0ENSTp/hbDTgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:14.281305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00290","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e9da7e7f006a6788147ced3b94113b1578e5a86c427a4d789d6f1c48eae8131","sha256:5d6b928515bb4366eb9e497558d9eb97e37d45010fd3a1fd75f395eae79d504e"],"state_sha256":"0d59c2d939de6ed4582a1f84bd9595ff7e11d489d877b135ec9b8f65a608676a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tg/BEAK1vW+4JAF98RCxgerHc1YPRgqFqdvtxS0EkOwf6uTe+rUf/J/MBoNle6MzSMqA3/uIEG86Ao0CZPUoDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:15:25.466110Z","bundle_sha256":"5d145c97caffb2beb5240ae7939617f19e4392b9c2f8da157bee97550585945b"}}