{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OARBYHR3FRR6UHCFDHOIXEL42P","short_pith_number":"pith:OARBYHR3","canonical_record":{"source":{"id":"2201.05609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T18:58:17Z","cross_cats_sorted":[],"title_canon_sha256":"fa4a021034596f1f0a0f13316a0fe3f1b141fa25f2e287839daaca2a29430521","abstract_canon_sha256":"8f8df73db289c372700614bc286e7502866323bf83ff1ad6fa3edef409bcd5e5"},"schema_version":"1.0"},"canonical_sha256":"70221c1e3b2c63ea1c4519dc8b917cd3fea6dd7b083753db62a6346c8451fa70","source":{"kind":"arxiv","id":"2201.05609","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05609","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05609v2","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05609","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"OARBYHR3FRR6","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"OARBYHR3FRR6UHCF","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"OARBYHR3","created_at":"2026-07-05T04:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OARBYHR3FRR6UHCFDHOIXEL42P","target":"record","payload":{"canonical_record":{"source":{"id":"2201.05609","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T18:58:17Z","cross_cats_sorted":[],"title_canon_sha256":"fa4a021034596f1f0a0f13316a0fe3f1b141fa25f2e287839daaca2a29430521","abstract_canon_sha256":"8f8df73db289c372700614bc286e7502866323bf83ff1ad6fa3edef409bcd5e5"},"schema_version":"1.0"},"canonical_sha256":"70221c1e3b2c63ea1c4519dc8b917cd3fea6dd7b083753db62a6346c8451fa70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:30:32.887575Z","signature_b64":"Z4sp5WNHjRb2pw6Ewy6cn5SEiOAVltBL3eIjvIufEU3lDLhQcxYG9OJsTN7hg9SbAl2pNWTcd854tWiudJW7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70221c1e3b2c63ea1c4519dc8b917cd3fea6dd7b083753db62a6346c8451fa70","last_reissued_at":"2026-07-05T04:30:32.887062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:30:32.887062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.05609","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":"2026-07-05T04:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3aTRUw+1uGOfK9F7B6OXME9wK5R/Uv+GOkGlPqxDEH0f9ofB0aBCUluOFUZXFX4Jpwxa5WjVWq9ACiSjviquDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:07:02.109261Z"},"content_sha256":"3da21dc4f0e10a9a9d81fd9ac36ed15ab308130f2aa8493c8a30313075ec9897","schema_version":"1.0","event_id":"sha256:3da21dc4f0e10a9a9d81fd9ac36ed15ab308130f2aa8493c8a30313075ec9897"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OARBYHR3FRR6UHCFDHOIXEL42P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Open Text Release 1: Public Domain News in 44 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chester Palen-Michel, Constantine Lignos, June Kim","submitted_at":"2022-01-14T18:58:17Z","abstract_excerpt":"We present Multilingual Open Text (MOT), a new multilingual corpus containing text in 44 languages, many of which have limited existing text resources for natural language processing. The first release of the corpus contains over 2.8 million news articles and an additional 1 million short snippets (photo captions, video descriptions, etc.) published between 2001--2022 and collected from Voice of America's news websites. We describe our process for collecting, filtering, and processing the data. The source material is in the public domain, our collection is licensed using a creative commons lic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05609","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/2201.05609/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":"2026-07-05T04:30:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYJzaNKubzC9dV/wsyg0Ppz5oNdB2LJDQzEcYJH5rW8p8CZBxkdYpYszb73KYNZvh8LkOE8w1yp20qLDWCjYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:07:02.109654Z"},"content_sha256":"b8cb29fcd6713844c53e67662599ef93df03d69a17d0c5c1abc2390cb8836218","schema_version":"1.0","event_id":"sha256:b8cb29fcd6713844c53e67662599ef93df03d69a17d0c5c1abc2390cb8836218"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OARBYHR3FRR6UHCFDHOIXEL42P/bundle.json","state_url":"https://pith.science/pith/OARBYHR3FRR6UHCFDHOIXEL42P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OARBYHR3FRR6UHCFDHOIXEL42P/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":"2026-07-08T18:07:02Z","links":{"resolver":"https://pith.science/pith/OARBYHR3FRR6UHCFDHOIXEL42P","bundle":"https://pith.science/pith/OARBYHR3FRR6UHCFDHOIXEL42P/bundle.json","state":"https://pith.science/pith/OARBYHR3FRR6UHCFDHOIXEL42P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OARBYHR3FRR6UHCFDHOIXEL42P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OARBYHR3FRR6UHCFDHOIXEL42P","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":"8f8df73db289c372700614bc286e7502866323bf83ff1ad6fa3edef409bcd5e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T18:58:17Z","title_canon_sha256":"fa4a021034596f1f0a0f13316a0fe3f1b141fa25f2e287839daaca2a29430521"},"schema_version":"1.0","source":{"id":"2201.05609","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.05609","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"arxiv_version","alias_value":"2201.05609v2","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05609","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"pith_short_12","alias_value":"OARBYHR3FRR6","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"OARBYHR3FRR6UHCF","created_at":"2026-07-05T04:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"OARBYHR3","created_at":"2026-07-05T04:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:b8cb29fcd6713844c53e67662599ef93df03d69a17d0c5c1abc2390cb8836218","target":"graph","created_at":"2026-07-05T04:30:32Z","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/2201.05609/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Multilingual Open Text (MOT), a new multilingual corpus containing text in 44 languages, many of which have limited existing text resources for natural language processing. The first release of the corpus contains over 2.8 million news articles and an additional 1 million short snippets (photo captions, video descriptions, etc.) published between 2001--2022 and collected from Voice of America's news websites. We describe our process for collecting, filtering, and processing the data. The source material is in the public domain, our collection is licensed using a creative commons lic","authors_text":"Chester Palen-Michel, Constantine Lignos, June Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T18:58:17Z","title":"Multilingual Open Text Release 1: Public Domain News in 44 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05609","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":"sha256:3da21dc4f0e10a9a9d81fd9ac36ed15ab308130f2aa8493c8a30313075ec9897","target":"record","created_at":"2026-07-05T04:30:32Z","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":"8f8df73db289c372700614bc286e7502866323bf83ff1ad6fa3edef409bcd5e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T18:58:17Z","title_canon_sha256":"fa4a021034596f1f0a0f13316a0fe3f1b141fa25f2e287839daaca2a29430521"},"schema_version":"1.0","source":{"id":"2201.05609","kind":"arxiv","version":2}},"canonical_sha256":"70221c1e3b2c63ea1c4519dc8b917cd3fea6dd7b083753db62a6346c8451fa70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70221c1e3b2c63ea1c4519dc8b917cd3fea6dd7b083753db62a6346c8451fa70","first_computed_at":"2026-07-05T04:30:32.887062Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:32.887062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z4sp5WNHjRb2pw6Ewy6cn5SEiOAVltBL3eIjvIufEU3lDLhQcxYG9OJsTN7hg9SbAl2pNWTcd854tWiudJW7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:32.887575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.05609","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3da21dc4f0e10a9a9d81fd9ac36ed15ab308130f2aa8493c8a30313075ec9897","sha256:b8cb29fcd6713844c53e67662599ef93df03d69a17d0c5c1abc2390cb8836218"],"state_sha256":"b4e15c7a83d99cc914e424abf443f413bc328caadb0561519989a408f2710b9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArpkPAd/6qq+bo7Bwfj7uuw4AVeRRhNNF3m7VahwKkcv/qjjfigtcUoLePRWz8Q8H1XQm0qBPkWGKO5tXRKJBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T18:07:02.112040Z","bundle_sha256":"237a0326a4053a189f4cf4733cbc187540840765e3769d1ffc56c0a0732f3878"}}