{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OL5QRLJTDJ4KBCXV56F3BDYKOA","short_pith_number":"pith:OL5QRLJT","canonical_record":{"source":{"id":"2409.05247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-08T23:51:04Z","cross_cats_sorted":[],"title_canon_sha256":"72add8c2a3341a5cccc6639dc78e5d3b5f707dc01944fe75488006f0db2284d8","abstract_canon_sha256":"e94e6b0c8fd363fa6cbaebe01bc0d9e4d8e75ac2161113185e898502efe340be"},"schema_version":"1.0"},"canonical_sha256":"72fb08ad331a78a08af5ef8bb08f0a703bcbd89b88d25e93ac8a5d7ab89c3cd2","source":{"kind":"arxiv","id":"2409.05247","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05247","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05247v1","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05247","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"OL5QRLJTDJ4K","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"OL5QRLJTDJ4KBCXV","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"OL5QRLJT","created_at":"2026-07-05T09:04:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OL5QRLJTDJ4KBCXV56F3BDYKOA","target":"record","payload":{"canonical_record":{"source":{"id":"2409.05247","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-08T23:51:04Z","cross_cats_sorted":[],"title_canon_sha256":"72add8c2a3341a5cccc6639dc78e5d3b5f707dc01944fe75488006f0db2284d8","abstract_canon_sha256":"e94e6b0c8fd363fa6cbaebe01bc0d9e4d8e75ac2161113185e898502efe340be"},"schema_version":"1.0"},"canonical_sha256":"72fb08ad331a78a08af5ef8bb08f0a703bcbd89b88d25e93ac8a5d7ab89c3cd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:46.600381Z","signature_b64":"JIsHhNKtbccAHZLEaVGCyoavgL9kcoMK5wl8C0J0E7Jc2O2eM6PDKg5Rj0c4kL+11M6huRDcuWfO7KZ4I32+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72fb08ad331a78a08af5ef8bb08f0a703bcbd89b88d25e93ac8a5d7ab89c3cd2","last_reissued_at":"2026-07-05T09:04:46.599942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:46.599942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.05247","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":"2026-07-05T09:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G44ZEjUo8+CKwG1ITOGOIUwWKDTpbPoT4rNf7QFUVMbB9oojcBXyLwmRWkJgKt0ZjuXf8pNwkoYw8v7jU3dbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:55:46.701055Z"},"content_sha256":"987d5bd694f4617e3360a4af767ba739c131b3d9a402d77b9ee79d9ed04b8edd","schema_version":"1.0","event_id":"sha256:987d5bd694f4617e3360a4af767ba739c131b3d9a402d77b9ee79d9ed04b8edd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OL5QRLJTDJ4KBCXV56F3BDYKOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Socially Responsible Data for Large Multilingual Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alex Zito, Amber Ebinama, Andrew Smart, Ben Hutchinson, Ding Wang, Edem Wornyo, Erin van Liemt, Jamila Smith-Loud, Jo\\~ao Sedoc, Lameck Mbangula Amugongo, Seyi Olojo, Sonja Schmer-Galunder, Stanley Uwakwe, Suzanne Dikker, Zara Wudiri","submitted_at":"2024-09-08T23:51:04Z","abstract_excerpt":"Large Language Models (LLMs) have rapidly increased in size and apparent capabilities in the last three years, but their training data is largely English text. There is growing interest in multilingual LLMs, and various efforts are striving for models to accommodate languages of communities outside of the Global North, which include many languages that have been historically underrepresented in digital realms. These languages have been coined as \"low resource languages\" or \"long-tail languages\", and LLMs performance on these languages is generally poor. While expanding the use of LLMs to more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05247","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/2409.05247/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":"2026-07-05T09:04:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lxX1IhHj7GEPjOgkzKLQFH4Fh6WhmaJwNEMQVctr9BsqUyjPyh35jkfj0hdJzJHam5XgefT0q0c1ePf7SJz3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T01:55:46.702000Z"},"content_sha256":"7bf17029f4386b114a7c54f0f9590791a7e980b8715ba4f27a561a37b3f46fce","schema_version":"1.0","event_id":"sha256:7bf17029f4386b114a7c54f0f9590791a7e980b8715ba4f27a561a37b3f46fce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA/bundle.json","state_url":"https://pith.science/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA/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":"2026-08-15T01:55:46Z","links":{"resolver":"https://pith.science/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA","bundle":"https://pith.science/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA/bundle.json","state":"https://pith.science/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OL5QRLJTDJ4KBCXV56F3BDYKOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OL5QRLJTDJ4KBCXV56F3BDYKOA","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":"e94e6b0c8fd363fa6cbaebe01bc0d9e4d8e75ac2161113185e898502efe340be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-08T23:51:04Z","title_canon_sha256":"72add8c2a3341a5cccc6639dc78e5d3b5f707dc01944fe75488006f0db2284d8"},"schema_version":"1.0","source":{"id":"2409.05247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.05247","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"arxiv_version","alias_value":"2409.05247v1","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.05247","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"pith_short_12","alias_value":"OL5QRLJTDJ4K","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"pith_short_16","alias_value":"OL5QRLJTDJ4KBCXV","created_at":"2026-07-05T09:04:46Z"},{"alias_kind":"pith_short_8","alias_value":"OL5QRLJT","created_at":"2026-07-05T09:04:46Z"}],"graph_snapshots":[{"event_id":"sha256:7bf17029f4386b114a7c54f0f9590791a7e980b8715ba4f27a561a37b3f46fce","target":"graph","created_at":"2026-07-05T09:04:46Z","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/2409.05247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have rapidly increased in size and apparent capabilities in the last three years, but their training data is largely English text. There is growing interest in multilingual LLMs, and various efforts are striving for models to accommodate languages of communities outside of the Global North, which include many languages that have been historically underrepresented in digital realms. These languages have been coined as \"low resource languages\" or \"long-tail languages\", and LLMs performance on these languages is generally poor. While expanding the use of LLMs to more ","authors_text":"Alex Zito, Amber Ebinama, Andrew Smart, Ben Hutchinson, Ding Wang, Edem Wornyo, Erin van Liemt, Jamila Smith-Loud, Jo\\~ao Sedoc, Lameck Mbangula Amugongo, Seyi Olojo, Sonja Schmer-Galunder, Stanley Uwakwe, Suzanne Dikker, Zara Wudiri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-08T23:51:04Z","title":"Socially Responsible Data for Large Multilingual Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.05247","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":"sha256:987d5bd694f4617e3360a4af767ba739c131b3d9a402d77b9ee79d9ed04b8edd","target":"record","created_at":"2026-07-05T09:04:46Z","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":"e94e6b0c8fd363fa6cbaebe01bc0d9e4d8e75ac2161113185e898502efe340be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-08T23:51:04Z","title_canon_sha256":"72add8c2a3341a5cccc6639dc78e5d3b5f707dc01944fe75488006f0db2284d8"},"schema_version":"1.0","source":{"id":"2409.05247","kind":"arxiv","version":1}},"canonical_sha256":"72fb08ad331a78a08af5ef8bb08f0a703bcbd89b88d25e93ac8a5d7ab89c3cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72fb08ad331a78a08af5ef8bb08f0a703bcbd89b88d25e93ac8a5d7ab89c3cd2","first_computed_at":"2026-07-05T09:04:46.599942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:46.599942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JIsHhNKtbccAHZLEaVGCyoavgL9kcoMK5wl8C0J0E7Jc2O2eM6PDKg5Rj0c4kL+11M6huRDcuWfO7KZ4I32+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:46.600381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.05247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:987d5bd694f4617e3360a4af767ba739c131b3d9a402d77b9ee79d9ed04b8edd","sha256:7bf17029f4386b114a7c54f0f9590791a7e980b8715ba4f27a561a37b3f46fce"],"state_sha256":"c8029dd5a19102264b11a8894bbb35d0da8c2a500311dcde3dc93ce4ceed5951"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/E//xsYmksYCsZ+XnO/9vH8XV58kYJIv67GmD6CnYz6v3GluookftcQfZu8QKwGlpfcUvNHCY8blJgDoeYD1DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T01:55:46.709422Z","bundle_sha256":"9993a1121796a06e60ec003337a71ff3ac4178d30b8d8e98debda66483718802"}}