{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3WGKDPJDOREO3PRJULEMU6GPAT","short_pith_number":"pith:3WGKDPJD","canonical_record":{"source":{"id":"1909.04181","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T22:08:12Z","cross_cats_sorted":[],"title_canon_sha256":"c44201cc29c519cb1c3f5350b25cfa6376ea834f4bc220d9460166ae83ac44a2","abstract_canon_sha256":"a96d26c7bb184e333a3013f25b3ad19a6c36841f233393c7e411f8842be18187"},"schema_version":"1.0"},"canonical_sha256":"dd8ca1bd237448edbe29a2c8ca78cf04d59281e9eb245cc402b81b74b4f6d483","source":{"kind":"arxiv","id":"1909.04181","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.04181","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"arxiv_version","alias_value":"1909.04181v3","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04181","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"pith_short_12","alias_value":"3WGKDPJDOREO","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"pith_short_16","alias_value":"3WGKDPJDOREO3PRJ","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"pith_short_8","alias_value":"3WGKDPJD","created_at":"2026-07-05T00:16:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3WGKDPJDOREO3PRJULEMU6GPAT","target":"record","payload":{"canonical_record":{"source":{"id":"1909.04181","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T22:08:12Z","cross_cats_sorted":[],"title_canon_sha256":"c44201cc29c519cb1c3f5350b25cfa6376ea834f4bc220d9460166ae83ac44a2","abstract_canon_sha256":"a96d26c7bb184e333a3013f25b3ad19a6c36841f233393c7e411f8842be18187"},"schema_version":"1.0"},"canonical_sha256":"dd8ca1bd237448edbe29a2c8ca78cf04d59281e9eb245cc402b81b74b4f6d483","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:05.547109Z","signature_b64":"YDFvZnn8leESoAmzjek8HM0vtUaMqB/RgsqtpIEHEn9FBF3cjV7FJaqeXw+aubhMVFXGNe71e+s2MzkPyfDWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd8ca1bd237448edbe29a2c8ca78cf04d59281e9eb245cc402b81b74b4f6d483","last_reissued_at":"2026-07-05T00:16:05.546697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:05.546697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.04181","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:16:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tdvJaQK9Mg5+m9OQDXjgjYnWoOE4zX9mDkenbg+9bxUY5Q17gZGd1yJb/ARMFoM71B7BqQ4BMwJOGVcI1x8jBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:27:58.886488Z"},"content_sha256":"7c184e04fe2939ff6195a4c7330e006afdf94b2338f3c4e8ea0521953b5f6c4f","schema_version":"1.0","event_id":"sha256:7c184e04fe2939ff6195a4c7330e006afdf94b2338f3c4e8ea0521953b5f6c4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3WGKDPJDOREO3PRJULEMU6GPAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BERT-Based Arabic Social Media Author Profiling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Muhammad Abdul-Mageed","submitted_at":"2019-09-09T22:08:12Z","abstract_excerpt":"We report our models for detecting age, language variety, and gender from social media data in the context of the Arabic author profiling and deception detection shared task (APDA). We build simple models based on pre-trained bidirectional encoders from transformers (BERT). We first fine-tune the pre-trained BERT model on each of the three datasets with shared task released data. Then we augment shared task data with in-house data for gender and dialect, showing the utility of augmenting training data. Our best models on the shared task test data are acquired with a majority voting of various "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04181","kind":"arxiv","version":3},"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/1909.04181/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":"2026-07-05T00:16:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4Ib4fcsU3SdUwlsMxfJaC8i9Wcsf4u79i2mRwKb9CXxGhY6DE77/o3rVB5GLVu0Aq4phSWAAW2sAlC80pRmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:27:58.886985Z"},"content_sha256":"c8c0049bdd389446a918efea95e6f64e91f64d4ab7aa5c2c8d088502ff40fe2a","schema_version":"1.0","event_id":"sha256:c8c0049bdd389446a918efea95e6f64e91f64d4ab7aa5c2c8d088502ff40fe2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WGKDPJDOREO3PRJULEMU6GPAT/bundle.json","state_url":"https://pith.science/pith/3WGKDPJDOREO3PRJULEMU6GPAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WGKDPJDOREO3PRJULEMU6GPAT/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":"2026-08-05T05:27:58Z","links":{"resolver":"https://pith.science/pith/3WGKDPJDOREO3PRJULEMU6GPAT","bundle":"https://pith.science/pith/3WGKDPJDOREO3PRJULEMU6GPAT/bundle.json","state":"https://pith.science/pith/3WGKDPJDOREO3PRJULEMU6GPAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WGKDPJDOREO3PRJULEMU6GPAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3WGKDPJDOREO3PRJULEMU6GPAT","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":"a96d26c7bb184e333a3013f25b3ad19a6c36841f233393c7e411f8842be18187","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T22:08:12Z","title_canon_sha256":"c44201cc29c519cb1c3f5350b25cfa6376ea834f4bc220d9460166ae83ac44a2"},"schema_version":"1.0","source":{"id":"1909.04181","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.04181","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"arxiv_version","alias_value":"1909.04181v3","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.04181","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"pith_short_12","alias_value":"3WGKDPJDOREO","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"pith_short_16","alias_value":"3WGKDPJDOREO3PRJ","created_at":"2026-07-05T00:16:05Z"},{"alias_kind":"pith_short_8","alias_value":"3WGKDPJD","created_at":"2026-07-05T00:16:05Z"}],"graph_snapshots":[{"event_id":"sha256:c8c0049bdd389446a918efea95e6f64e91f64d4ab7aa5c2c8d088502ff40fe2a","target":"graph","created_at":"2026-07-05T00:16:05Z","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/1909.04181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We report our models for detecting age, language variety, and gender from social media data in the context of the Arabic author profiling and deception detection shared task (APDA). We build simple models based on pre-trained bidirectional encoders from transformers (BERT). We first fine-tune the pre-trained BERT model on each of the three datasets with shared task released data. Then we augment shared task data with in-house data for gender and dialect, showing the utility of augmenting training data. Our best models on the shared task test data are acquired with a majority voting of various ","authors_text":"Chiyu Zhang, Muhammad Abdul-Mageed","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T22:08:12Z","title":"BERT-Based Arabic Social Media Author Profiling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.04181","kind":"arxiv","version":3},"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":"sha256:7c184e04fe2939ff6195a4c7330e006afdf94b2338f3c4e8ea0521953b5f6c4f","target":"record","created_at":"2026-07-05T00:16:05Z","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":"a96d26c7bb184e333a3013f25b3ad19a6c36841f233393c7e411f8842be18187","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T22:08:12Z","title_canon_sha256":"c44201cc29c519cb1c3f5350b25cfa6376ea834f4bc220d9460166ae83ac44a2"},"schema_version":"1.0","source":{"id":"1909.04181","kind":"arxiv","version":3}},"canonical_sha256":"dd8ca1bd237448edbe29a2c8ca78cf04d59281e9eb245cc402b81b74b4f6d483","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd8ca1bd237448edbe29a2c8ca78cf04d59281e9eb245cc402b81b74b4f6d483","first_computed_at":"2026-07-05T00:16:05.546697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:05.546697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDFvZnn8leESoAmzjek8HM0vtUaMqB/RgsqtpIEHEn9FBF3cjV7FJaqeXw+aubhMVFXGNe71e+s2MzkPyfDWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:05.547109Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.04181","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c184e04fe2939ff6195a4c7330e006afdf94b2338f3c4e8ea0521953b5f6c4f","sha256:c8c0049bdd389446a918efea95e6f64e91f64d4ab7aa5c2c8d088502ff40fe2a"],"state_sha256":"5e6423a1cd880ea60ee9d6bd18d5bb87f1c23d69cf9ce0a4d9794e7044132237"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFiXdHKBpe/2PlLDfswfSRmO1RPACc6EoaAc6La7wafHxZn6ByVDVIraZ4FGl6qoNDIrI6E0p8dp1h1mCaxTCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:27:58.891662Z","bundle_sha256":"9ba6232664509d2b96edd36dbfb2f80ce3a908f244779d12aff2577c015ec18f"}}