{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VA2JH667HMSZRPCR6DXKFKUP6K","short_pith_number":"pith:VA2JH667","canonical_record":{"source":{"id":"1708.07903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-08-25T22:03:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"11aa5f6a8770ad29627c397d63e28929f0cac522d40a0c659c0a42fc364b7513","abstract_canon_sha256":"81f07f52037b537c600044983185078e060e161a069dde5f90c23894d0702ebe"},"schema_version":"1.0"},"canonical_sha256":"a83493fbdf3b2598bc51f0eea2aa8ff29e2a6e72d56f5114c0644449f42850ba","source":{"kind":"arxiv","id":"1708.07903","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.07903","created_at":"2026-05-18T00:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"1708.07903v1","created_at":"2026-05-18T00:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07903","created_at":"2026-05-18T00:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"VA2JH667HMSZ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VA2JH667HMSZRPCR","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VA2JH667","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VA2JH667HMSZRPCR6DXKFKUP6K","target":"record","payload":{"canonical_record":{"source":{"id":"1708.07903","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-08-25T22:03:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"11aa5f6a8770ad29627c397d63e28929f0cac522d40a0c659c0a42fc364b7513","abstract_canon_sha256":"81f07f52037b537c600044983185078e060e161a069dde5f90c23894d0702ebe"},"schema_version":"1.0"},"canonical_sha256":"a83493fbdf3b2598bc51f0eea2aa8ff29e2a6e72d56f5114c0644449f42850ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:37.679012Z","signature_b64":"B0th/6a/qbECw7ZXsO0Z1ZAwlK7ifW4Ojf2xRSJf8aPMZju7rJ050sisonWATxqOs0NLMn7+I0kPuLAujKTUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a83493fbdf3b2598bc51f0eea2aa8ff29e2a6e72d56f5114c0644449f42850ba","last_reissued_at":"2026-05-18T00:36:37.678352Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:37.678352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.07903","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":"2026-05-18T00:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bfzP/dgfKw5ofwhMGnDzj46EchtbZlZePygcOOH6c2VEgzRLxhs/MNZLyN56+WGAYUB/gHsh9ZqjR+zwmyq1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:53:34.093584Z"},"content_sha256":"8aee33a2554f0d0dfef9c629bbe5c7460a7bd87734fe5f941b0f083e8e5be439","schema_version":"1.0","event_id":"sha256:8aee33a2554f0d0dfef9c629bbe5c7460a7bd87734fe5f941b0f083e8e5be439"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VA2JH667HMSZRPCR6DXKFKUP6K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nationality Classification Using Name Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SI","authors_text":"Baris Coskun, Hong Qin, Junting Ye, Meizhu Liu, Shuchu Han, Steven Skiena, Yifan Hu","submitted_at":"2017-08-25T22:03:09Z","abstract_excerpt":"Nationality identification unlocks important demographic information, with many applications in biomedical and sociological research. Existing name-based nationality classifiers use name substrings as features and are trained on small, unrepresentative sets of labeled names, typically extracted from Wikipedia. As a result, these methods achieve limited performance and cannot support fine-grained classification.\n  We exploit the phenomena of homophily in communication patterns to learn name embeddings, a new representation that encodes gender, ethnicity, and nationality which is readily applica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07903","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":""},"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":"2026-05-18T00:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ByM6YvP8EOA3B8GnTiPUneq2bBqBks3q8wR7xWAm+72FNxryaCopb4pWPMJaqLpGpOP8tBIqNN+RnrSbePgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T16:53:34.094369Z"},"content_sha256":"6306d20ce3525ad77492a744b26cbaf82cbb883b7257d12bc5379fc70acebf85","schema_version":"1.0","event_id":"sha256:6306d20ce3525ad77492a744b26cbaf82cbb883b7257d12bc5379fc70acebf85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VA2JH667HMSZRPCR6DXKFKUP6K/bundle.json","state_url":"https://pith.science/pith/VA2JH667HMSZRPCR6DXKFKUP6K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VA2JH667HMSZRPCR6DXKFKUP6K/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":"2026-05-31T16:53:34Z","links":{"resolver":"https://pith.science/pith/VA2JH667HMSZRPCR6DXKFKUP6K","bundle":"https://pith.science/pith/VA2JH667HMSZRPCR6DXKFKUP6K/bundle.json","state":"https://pith.science/pith/VA2JH667HMSZRPCR6DXKFKUP6K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VA2JH667HMSZRPCR6DXKFKUP6K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VA2JH667HMSZRPCR6DXKFKUP6K","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":"81f07f52037b537c600044983185078e060e161a069dde5f90c23894d0702ebe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-08-25T22:03:09Z","title_canon_sha256":"11aa5f6a8770ad29627c397d63e28929f0cac522d40a0c659c0a42fc364b7513"},"schema_version":"1.0","source":{"id":"1708.07903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.07903","created_at":"2026-05-18T00:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"1708.07903v1","created_at":"2026-05-18T00:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.07903","created_at":"2026-05-18T00:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"VA2JH667HMSZ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VA2JH667HMSZRPCR","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VA2JH667","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:6306d20ce3525ad77492a744b26cbaf82cbb883b7257d12bc5379fc70acebf85","target":"graph","created_at":"2026-05-18T00:36:37Z","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"},"paper":{"abstract_excerpt":"Nationality identification unlocks important demographic information, with many applications in biomedical and sociological research. Existing name-based nationality classifiers use name substrings as features and are trained on small, unrepresentative sets of labeled names, typically extracted from Wikipedia. As a result, these methods achieve limited performance and cannot support fine-grained classification.\n  We exploit the phenomena of homophily in communication patterns to learn name embeddings, a new representation that encodes gender, ethnicity, and nationality which is readily applica","authors_text":"Baris Coskun, Hong Qin, Junting Ye, Meizhu Liu, Shuchu Han, Steven Skiena, Yifan Hu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-08-25T22:03:09Z","title":"Nationality Classification Using Name Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.07903","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":"sha256:8aee33a2554f0d0dfef9c629bbe5c7460a7bd87734fe5f941b0f083e8e5be439","target":"record","created_at":"2026-05-18T00:36:37Z","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":"81f07f52037b537c600044983185078e060e161a069dde5f90c23894d0702ebe","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2017-08-25T22:03:09Z","title_canon_sha256":"11aa5f6a8770ad29627c397d63e28929f0cac522d40a0c659c0a42fc364b7513"},"schema_version":"1.0","source":{"id":"1708.07903","kind":"arxiv","version":1}},"canonical_sha256":"a83493fbdf3b2598bc51f0eea2aa8ff29e2a6e72d56f5114c0644449f42850ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a83493fbdf3b2598bc51f0eea2aa8ff29e2a6e72d56f5114c0644449f42850ba","first_computed_at":"2026-05-18T00:36:37.678352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:37.678352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0th/6a/qbECw7ZXsO0Z1ZAwlK7ifW4Ojf2xRSJf8aPMZju7rJ050sisonWATxqOs0NLMn7+I0kPuLAujKTUBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:37.679012Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.07903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8aee33a2554f0d0dfef9c629bbe5c7460a7bd87734fe5f941b0f083e8e5be439","sha256:6306d20ce3525ad77492a744b26cbaf82cbb883b7257d12bc5379fc70acebf85"],"state_sha256":"66687f5eaa00294c6cc5ad0104d9f7dde9be8ce97ca8b5f60037f5846d844a36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1TMizRK8z4wWPescyBxA/00g5HkMrsO8e9IWlwvfgc8TJTCHl3L4kFYhSY7a+CCheVuc1a8TPmcRG1BM6RymCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T16:53:34.098416Z","bundle_sha256":"5ec9bfb2f677e47996e130b880ee759e3c94588a8da4b8d0b4440e794581d1df"}}