{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HW42DZ3E6EH3EOAMOZXUBDQVXO","short_pith_number":"pith:HW42DZ3E","canonical_record":{"source":{"id":"1805.03122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-08T15:50:32Z","cross_cats_sorted":[],"title_canon_sha256":"5954e32f13cf143681c7b82531662fc7f9d9a7aa267db5e0108a4b4e30eee631","abstract_canon_sha256":"0521cf1563c94ee15a30f7052b4cc63f4778e824ca6ecf3a5fced4caaa93213a"},"schema_version":"1.0"},"canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","source":{"kind":"arxiv","id":"1805.03122","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03122","created_at":"2026-05-18T00:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03122v1","created_at":"2026-05-18T00:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03122","created_at":"2026-05-18T00:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"HW42DZ3E6EH3","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HW42DZ3E6EH3EOAM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HW42DZ3E","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HW42DZ3E6EH3EOAMOZXUBDQVXO","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-08T15:50:32Z","cross_cats_sorted":[],"title_canon_sha256":"5954e32f13cf143681c7b82531662fc7f9d9a7aa267db5e0108a4b4e30eee631","abstract_canon_sha256":"0521cf1563c94ee15a30f7052b4cc63f4778e824ca6ecf3a5fced4caaa93213a"},"schema_version":"1.0"},"canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:34.546667Z","signature_b64":"uEVZXUucARW9a7Q5p+cNvSgTrlWfOpI3Vhmh1V8XFY+ua1U8Mf0DLKseq6gEFC6Q6dPkbpYuN1YSd4L6343mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","last_reissued_at":"2026-05-18T00:16:34.545960Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:34.545960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03122","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":"2026-05-18T00:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qyd4bhOyJv5UUTEkKKIpsXXrFOsKJVX+yTgQvRAHExPU4IeJoBRoi/IGOsfuwAwsbrlgMW6UzsaOsIVo+cHHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:49:27.587087Z"},"content_sha256":"40261e541d928b1bfac2fba6a8e530b110ae2baef51fb1fff8191647a23c7a2d","schema_version":"1.0","event_id":"sha256:40261e541d928b1bfac2fba6a8e530b110ae2baef51fb1fff8191647a23c7a2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HW42DZ3E6EH3EOAMOZXUBDQVXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bleaching Text: Abstract Features for Cross-lingual Gender Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barbara Plank, Ian Matroos, Malvina Nissim, Nikola Ljube\\v{s}i\\'c, Rob van der Goot","submitted_at":"2018-05-08T15:50:32Z","abstract_excerpt":"Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03122","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":"2026-05-18T00:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RImfVAnBUqyHmzPfigTX8Cunq+faXnWCRRLkH/rFMef6I+a1lQcnl1P9xPD9MEw6ewVMl0Ci0gIM/JfHiVPiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:49:27.587441Z"},"content_sha256":"dff91b01e16fef69aa77a8e828ef57e2e22822ee4ed7755f669a357ef0b41257","schema_version":"1.0","event_id":"sha256:dff91b01e16fef69aa77a8e828ef57e2e22822ee4ed7755f669a357ef0b41257"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/bundle.json","state_url":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/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":"2026-06-01T07:49:27Z","links":{"resolver":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO","bundle":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/bundle.json","state":"https://pith.science/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HW42DZ3E6EH3EOAMOZXUBDQVXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HW42DZ3E6EH3EOAMOZXUBDQVXO","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":"0521cf1563c94ee15a30f7052b4cc63f4778e824ca6ecf3a5fced4caaa93213a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-08T15:50:32Z","title_canon_sha256":"5954e32f13cf143681c7b82531662fc7f9d9a7aa267db5e0108a4b4e30eee631"},"schema_version":"1.0","source":{"id":"1805.03122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03122","created_at":"2026-05-18T00:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03122v1","created_at":"2026-05-18T00:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03122","created_at":"2026-05-18T00:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"HW42DZ3E6EH3","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HW42DZ3E6EH3EOAM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HW42DZ3E","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:dff91b01e16fef69aa77a8e828ef57e2e22822ee4ed7755f669a357ef0b41257","target":"graph","created_at":"2026-05-18T00:16:34Z","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":"Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent. Cross-lingual embeddings circumvent some of these limitations, but capture gender-specific style less. We propose an alternative: bleaching text, i.e., transforming lexical strings into more abstract features. This study provides evidence that such features allow for better transfer across languages. Moreover, we present a first study on the ability of humans to perform cross-lingual gender prediction. We find that human","authors_text":"Barbara Plank, Ian Matroos, Malvina Nissim, Nikola Ljube\\v{s}i\\'c, Rob van der Goot","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-08T15:50:32Z","title":"Bleaching Text: Abstract Features for Cross-lingual Gender Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03122","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":"sha256:40261e541d928b1bfac2fba6a8e530b110ae2baef51fb1fff8191647a23c7a2d","target":"record","created_at":"2026-05-18T00:16:34Z","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":"0521cf1563c94ee15a30f7052b4cc63f4778e824ca6ecf3a5fced4caaa93213a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-08T15:50:32Z","title_canon_sha256":"5954e32f13cf143681c7b82531662fc7f9d9a7aa267db5e0108a4b4e30eee631"},"schema_version":"1.0","source":{"id":"1805.03122","kind":"arxiv","version":1}},"canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3db9a1e764f10fb2380c766f408e15bba71d06758208b0f7fa9e66be14a13072","first_computed_at":"2026-05-18T00:16:34.545960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:34.545960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uEVZXUucARW9a7Q5p+cNvSgTrlWfOpI3Vhmh1V8XFY+ua1U8Mf0DLKseq6gEFC6Q6dPkbpYuN1YSd4L6343mCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:34.546667Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40261e541d928b1bfac2fba6a8e530b110ae2baef51fb1fff8191647a23c7a2d","sha256:dff91b01e16fef69aa77a8e828ef57e2e22822ee4ed7755f669a357ef0b41257"],"state_sha256":"c5007d7a0280c27aaf1bb3f30df3730c5c78f84c238771923cd1b5ece174d7ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thba2q7BFxDPdUaeJ6DfiXa5ILcfaSFzpa4kYiMu5MGRM/rnyLqxRx9jGi2EqYifmfHHWoYrBo2bYSu9ejoQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:49:27.589277Z","bundle_sha256":"4388459f5120b4a8657d2488385018055c43cab81c19c492af6c2604ada79a14"}}