{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ORWE4GPY2KXWJOOTZQ7ZYUA6W2","short_pith_number":"pith:ORWE4GPY","canonical_record":{"source":{"id":"2406.10258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T17:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"e5634632ac5016e4aba1ca3bcdfc1cb591a8730c4c4f201b0ab132d2420453bf","abstract_canon_sha256":"e26ceabdf97ecf8103b50035af7540fc242f779171918a2cde873c62fa26818f"},"schema_version":"1.0"},"canonical_sha256":"746c4e19f8d2af64b9d3cc3f9c501eb6852269f84775ca31dcae8ef34c9256e2","source":{"kind":"arxiv","id":"2406.10258","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10258","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10258v2","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10258","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_12","alias_value":"ORWE4GPY2KXW","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_16","alias_value":"ORWE4GPY2KXWJOOT","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_8","alias_value":"ORWE4GPY","created_at":"2026-07-05T08:33:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ORWE4GPY2KXWJOOTZQ7ZYUA6W2","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T17:59:11Z","cross_cats_sorted":[],"title_canon_sha256":"e5634632ac5016e4aba1ca3bcdfc1cb591a8730c4c4f201b0ab132d2420453bf","abstract_canon_sha256":"e26ceabdf97ecf8103b50035af7540fc242f779171918a2cde873c62fa26818f"},"schema_version":"1.0"},"canonical_sha256":"746c4e19f8d2af64b9d3cc3f9c501eb6852269f84775ca31dcae8ef34c9256e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:41.157114Z","signature_b64":"yVf/HVyxDc3wYk/TgJQPZ7OpTfT+RzeSYfcX1rC0+ktYKvYLgYyla0kNORh806fPicRBO0/B9P7dNpJfG/W4Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"746c4e19f8d2af64b9d3cc3f9c501eb6852269f84775ca31dcae8ef34c9256e2","last_reissued_at":"2026-07-05T08:33:41.156622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:41.156622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10258","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":"2026-07-05T08:33:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlgtOFSrbCrQ/TlvlvMAw8TabnYm8mJUwv/nrKUy+OWkiwAnk19CYJcqSVMQ3HWUSBgOTN4wgmztTaBK1nnmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:00:27.052195Z"},"content_sha256":"534d31e26dd33a5e7c4c2a58ed85eff620ed540143f489bbc9f557eb0d659dd8","schema_version":"1.0","event_id":"sha256:534d31e26dd33a5e7c4c2a58ed85eff620ed540143f489bbc9f557eb0d659dd8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ORWE4GPY2KXWJOOTZQ7ZYUA6W2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curating Grounded Synthetic Data with Global Perspectives for Equitable AI","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elin T\\\"ornquist, Robert Alexander Caulk","submitted_at":"2024-06-10T17:59:11Z","abstract_excerpt":"The development of robust AI models relies heavily on the quality and variety of training data available. In fields where data scarcity is prevalent, synthetic data generation offers a vital solution. In this paper, we introduce a novel approach to creating synthetic datasets, grounded in real-world diversity and enriched through strategic diversification. We synthesize data using a comprehensive collection of news articles spanning 12 languages and originating from 125 countries, to ensure a breadth of linguistic and cultural representations. Through enforced topic diversification, translatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10258","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/2406.10258/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":"2026-07-05T08:33:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9d7o8MzOIMCvTo+1wmwDYaewuxN9X/yGdlBIB5eNaO7yIxsuu/iOz+Rv71jHRCxx8GIMFON+r2qIMSDUIodsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:00:27.054293Z"},"content_sha256":"e94728a5be4484bbc05de81c44650a10fca5aa932bb36ee8be0270cc258fba70","schema_version":"1.0","event_id":"sha256:e94728a5be4484bbc05de81c44650a10fca5aa932bb36ee8be0270cc258fba70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2/bundle.json","state_url":"https://pith.science/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2/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":"2026-08-19T15:00:27Z","links":{"resolver":"https://pith.science/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2","bundle":"https://pith.science/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2/bundle.json","state":"https://pith.science/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORWE4GPY2KXWJOOTZQ7ZYUA6W2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ORWE4GPY2KXWJOOTZQ7ZYUA6W2","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":"e26ceabdf97ecf8103b50035af7540fc242f779171918a2cde873c62fa26818f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T17:59:11Z","title_canon_sha256":"e5634632ac5016e4aba1ca3bcdfc1cb591a8730c4c4f201b0ab132d2420453bf"},"schema_version":"1.0","source":{"id":"2406.10258","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10258","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10258v2","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10258","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_12","alias_value":"ORWE4GPY2KXW","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_16","alias_value":"ORWE4GPY2KXWJOOT","created_at":"2026-07-05T08:33:41Z"},{"alias_kind":"pith_short_8","alias_value":"ORWE4GPY","created_at":"2026-07-05T08:33:41Z"}],"graph_snapshots":[{"event_id":"sha256:e94728a5be4484bbc05de81c44650a10fca5aa932bb36ee8be0270cc258fba70","target":"graph","created_at":"2026-07-05T08:33:41Z","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/2406.10258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of robust AI models relies heavily on the quality and variety of training data available. In fields where data scarcity is prevalent, synthetic data generation offers a vital solution. In this paper, we introduce a novel approach to creating synthetic datasets, grounded in real-world diversity and enriched through strategic diversification. We synthesize data using a comprehensive collection of news articles spanning 12 languages and originating from 125 countries, to ensure a breadth of linguistic and cultural representations. Through enforced topic diversification, translatio","authors_text":"Elin T\\\"ornquist, Robert Alexander Caulk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T17:59:11Z","title":"Curating Grounded Synthetic Data with Global Perspectives for Equitable AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10258","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":"sha256:534d31e26dd33a5e7c4c2a58ed85eff620ed540143f489bbc9f557eb0d659dd8","target":"record","created_at":"2026-07-05T08:33:41Z","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":"e26ceabdf97ecf8103b50035af7540fc242f779171918a2cde873c62fa26818f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T17:59:11Z","title_canon_sha256":"e5634632ac5016e4aba1ca3bcdfc1cb591a8730c4c4f201b0ab132d2420453bf"},"schema_version":"1.0","source":{"id":"2406.10258","kind":"arxiv","version":2}},"canonical_sha256":"746c4e19f8d2af64b9d3cc3f9c501eb6852269f84775ca31dcae8ef34c9256e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"746c4e19f8d2af64b9d3cc3f9c501eb6852269f84775ca31dcae8ef34c9256e2","first_computed_at":"2026-07-05T08:33:41.156622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:41.156622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yVf/HVyxDc3wYk/TgJQPZ7OpTfT+RzeSYfcX1rC0+ktYKvYLgYyla0kNORh806fPicRBO0/B9P7dNpJfG/W4Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:41.157114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10258","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:534d31e26dd33a5e7c4c2a58ed85eff620ed540143f489bbc9f557eb0d659dd8","sha256:e94728a5be4484bbc05de81c44650a10fca5aa932bb36ee8be0270cc258fba70"],"state_sha256":"6a3528293a69ec018a5ddb29ce40fffa5b1cf92d179af25608e8915c27a7bc33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7iMTrYOKE/MvAG7qdzOb8FRYUrlPlhAmc8Q825043Dr7qp3RWay3fZbighwKsSCO2uZt3zAZCkNLjASs5W9lAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:00:27.066127Z","bundle_sha256":"5e34408e02c341255cb83f7ead7f78e7e472a893d53781db5e44f1ca99784794"}}