{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TBLQLUP66YAZCGGYWCR2VGFPOL","short_pith_number":"pith:TBLQLUP6","canonical_record":{"source":{"id":"2210.14712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T13:45:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4cd3b7da42aa631b8a75426a1a8c2ff31d47186ba0d9ccd1d857e05b928b160","abstract_canon_sha256":"b10f3dfd6e84f2bc04e3450fc8403b351f731c02d4c796037741506fe75c7999"},"schema_version":"1.0"},"canonical_sha256":"985705d1fef6019118d8b0a3aa98af72d8c20513c311e20b08827290a3614caf","source":{"kind":"arxiv","id":"2210.14712","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14712","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14712v1","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14712","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"TBLQLUP66YAZ","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"TBLQLUP66YAZCGGY","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"TBLQLUP6","created_at":"2026-07-05T05:10:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TBLQLUP66YAZCGGYWCR2VGFPOL","target":"record","payload":{"canonical_record":{"source":{"id":"2210.14712","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T13:45:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4cd3b7da42aa631b8a75426a1a8c2ff31d47186ba0d9ccd1d857e05b928b160","abstract_canon_sha256":"b10f3dfd6e84f2bc04e3450fc8403b351f731c02d4c796037741506fe75c7999"},"schema_version":"1.0"},"canonical_sha256":"985705d1fef6019118d8b0a3aa98af72d8c20513c311e20b08827290a3614caf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:48.907182Z","signature_b64":"HDjEZO/cekdwnZNVlbMzkLjgCEzPnnS+uB5jmPjVBY+N1tgZVtzOvZU+ioWwlRqa9OqvzL+l4rBFFtZNu52fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"985705d1fef6019118d8b0a3aa98af72d8c20513c311e20b08827290a3614caf","last_reissued_at":"2026-07-05T05:10:48.906787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:48.906787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.14712","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":"2026-07-05T05:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IkyWxYE+cyw+jF/VGp7ABp7e5gVc7QBXuMtAK4pmX9A8Pepq5zqwhpRJ71t4eHk1Zdxmk73C1N0VxlZCfY5TDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:24:36.533694Z"},"content_sha256":"1aeba2f1cc121d05e709044a48745e711456931908b7eabb4c336f1af3e840a8","schema_version":"1.0","event_id":"sha256:1aeba2f1cc121d05e709044a48745e711456931908b7eabb4c336f1af3e840a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TBLQLUP66YAZCGGYWCR2VGFPOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abraham Owodunni, Anna Filighera, Colin Leong, Daniel Whitenack, Jacob Mansdorfer, Joshua Nemecek","submitted_at":"2022-10-26T13:45:14Z","abstract_excerpt":"We present Bloom Library, a linguistically diverse set of multimodal and multilingual datasets for language modeling, image captioning, visual storytelling, and speech synthesis/recognition. These datasets represent either the most, or among the most, multilingual datasets for each of the included downstream tasks. In total, the initial release of the Bloom Library datasets covers 363 languages across 32 language families. We train downstream task models for various languages represented in the data, showing the viability of the data for future work in low-resource, multimodal NLP and establis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14712","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.14712/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":"2026-07-05T05:10:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YsHC3E3MuNOQExiHRAOruaVH6lzpvcq9rJ0DZNSFrMPV67PAyPfavAMUE0YfQrAbQkIFDoDL2QaxeLkKe2nnAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:24:36.534220Z"},"content_sha256":"6f6987f0271940162472f3e959bd28924effa52917edf388d02da8d07e0479cf","schema_version":"1.0","event_id":"sha256:6f6987f0271940162472f3e959bd28924effa52917edf388d02da8d07e0479cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBLQLUP66YAZCGGYWCR2VGFPOL/bundle.json","state_url":"https://pith.science/pith/TBLQLUP66YAZCGGYWCR2VGFPOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBLQLUP66YAZCGGYWCR2VGFPOL/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":"2026-08-11T01:24:36Z","links":{"resolver":"https://pith.science/pith/TBLQLUP66YAZCGGYWCR2VGFPOL","bundle":"https://pith.science/pith/TBLQLUP66YAZCGGYWCR2VGFPOL/bundle.json","state":"https://pith.science/pith/TBLQLUP66YAZCGGYWCR2VGFPOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBLQLUP66YAZCGGYWCR2VGFPOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TBLQLUP66YAZCGGYWCR2VGFPOL","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":"b10f3dfd6e84f2bc04e3450fc8403b351f731c02d4c796037741506fe75c7999","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T13:45:14Z","title_canon_sha256":"c4cd3b7da42aa631b8a75426a1a8c2ff31d47186ba0d9ccd1d857e05b928b160"},"schema_version":"1.0","source":{"id":"2210.14712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.14712","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"arxiv_version","alias_value":"2210.14712v1","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14712","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"pith_short_12","alias_value":"TBLQLUP66YAZ","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"pith_short_16","alias_value":"TBLQLUP66YAZCGGY","created_at":"2026-07-05T05:10:48Z"},{"alias_kind":"pith_short_8","alias_value":"TBLQLUP6","created_at":"2026-07-05T05:10:48Z"}],"graph_snapshots":[{"event_id":"sha256:6f6987f0271940162472f3e959bd28924effa52917edf388d02da8d07e0479cf","target":"graph","created_at":"2026-07-05T05:10:48Z","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/2210.14712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Bloom Library, a linguistically diverse set of multimodal and multilingual datasets for language modeling, image captioning, visual storytelling, and speech synthesis/recognition. These datasets represent either the most, or among the most, multilingual datasets for each of the included downstream tasks. In total, the initial release of the Bloom Library datasets covers 363 languages across 32 language families. We train downstream task models for various languages represented in the data, showing the viability of the data for future work in low-resource, multimodal NLP and establis","authors_text":"Abraham Owodunni, Anna Filighera, Colin Leong, Daniel Whitenack, Jacob Mansdorfer, Joshua Nemecek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T13:45:14Z","title":"Bloom Library: Multimodal Datasets in 300+ Languages for a Variety of Downstream Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14712","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":"sha256:1aeba2f1cc121d05e709044a48745e711456931908b7eabb4c336f1af3e840a8","target":"record","created_at":"2026-07-05T05:10:48Z","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":"b10f3dfd6e84f2bc04e3450fc8403b351f731c02d4c796037741506fe75c7999","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-26T13:45:14Z","title_canon_sha256":"c4cd3b7da42aa631b8a75426a1a8c2ff31d47186ba0d9ccd1d857e05b928b160"},"schema_version":"1.0","source":{"id":"2210.14712","kind":"arxiv","version":1}},"canonical_sha256":"985705d1fef6019118d8b0a3aa98af72d8c20513c311e20b08827290a3614caf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"985705d1fef6019118d8b0a3aa98af72d8c20513c311e20b08827290a3614caf","first_computed_at":"2026-07-05T05:10:48.906787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:10:48.906787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HDjEZO/cekdwnZNVlbMzkLjgCEzPnnS+uB5jmPjVBY+N1tgZVtzOvZU+ioWwlRqa9OqvzL+l4rBFFtZNu52fDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:10:48.907182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.14712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aeba2f1cc121d05e709044a48745e711456931908b7eabb4c336f1af3e840a8","sha256:6f6987f0271940162472f3e959bd28924effa52917edf388d02da8d07e0479cf"],"state_sha256":"a51026341cf0b7be4c3f5a3d9d49b402865000d9f4afebb349cb291689417866"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BNW+ouYF0VwIfsS2bIzcWpwGD05YQDac0TqeOodL/efK2myaShh0ZWh90cwNt7INugrYkkAM6mpn3x19aPIfAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:24:36.538375Z","bundle_sha256":"18ac2d9c4501ddbec5721765e55015964de908f7c42fff932e0f1fd862717df6"}}