{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QSTBSW5V2MKG6KCRRFERE6ND56","short_pith_number":"pith:QSTBSW5V","canonical_record":{"source":{"id":"1910.14243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-10-31T03:56:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"955052a258f190a1ca90655a6ab016d70d30872b67cc902a62a69440e0da393c","abstract_canon_sha256":"6b5e863c4a4b16d2f3067409f13964e226ad7316ea157c8a020cf94ac5eec53f"},"schema_version":"1.0"},"canonical_sha256":"84a6195bb5d3146f285189491279a3efb9ce31ac974ba06ea94f71124ef5f59b","source":{"kind":"arxiv","id":"1910.14243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.14243","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"1910.14243v1","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14243","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"QSTBSW5V2MKG","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"QSTBSW5V2MKG6KCR","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"QSTBSW5V","created_at":"2026-07-05T00:16:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QSTBSW5V2MKG6KCRRFERE6ND56","target":"record","payload":{"canonical_record":{"source":{"id":"1910.14243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-10-31T03:56:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"955052a258f190a1ca90655a6ab016d70d30872b67cc902a62a69440e0da393c","abstract_canon_sha256":"6b5e863c4a4b16d2f3067409f13964e226ad7316ea157c8a020cf94ac5eec53f"},"schema_version":"1.0"},"canonical_sha256":"84a6195bb5d3146f285189491279a3efb9ce31ac974ba06ea94f71124ef5f59b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:08.971520Z","signature_b64":"Dk8jZtRr5bU9g9sDCgjA/iwazKSSUZQSJ6SN3Am/Pd6u1EYj0GpUD4UJLhm8WPN/vmuG0oySbkWPIutf0/vMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84a6195bb5d3146f285189491279a3efb9ce31ac974ba06ea94f71124ef5f59b","last_reissued_at":"2026-07-05T00:16:08.971105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:08.971105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.14243","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":"2026-07-05T00:16:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XJ0LnOdW4pbWje3gm0aI00CfY6O2c57s30fecxEXrMrNjdSSDWdKywGPCbimP2PHY9KTgHUbaMrxhqCz8R/MCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:38:46.201595Z"},"content_sha256":"5581a53a67ff1510565a52c9c1367984b85112fb8670ccf4c6a968e7122819b3","schema_version":"1.0","event_id":"sha256:5581a53a67ff1510565a52c9c1367984b85112fb8670ccf4c6a968e7122819b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QSTBSW5V2MKG6KCRRFERE6ND56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Arun Rajendran, Chiyu Zhang, Lyle Ungar, Muhammad Abdul-Mageed","submitted_at":"2019-10-31T03:56:32Z","abstract_excerpt":"Prediction of language varieties and dialects is an important language processing task, with a wide range of applications. For Arabic, the native tongue of ~ 300 million people, most varieties remain unsupported. To ease this bottleneck, we present a very large scale dataset covering 319 cities from all 21 Arab countries. We introduce a hierarchical attention multi-task learning (HA-MTL) approach for dialect identification exploiting our data at the city, state, and country levels. We also evaluate use of BERT on the three tasks, comparing it to the MTL approach. We benchmark and release our d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14243","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/1910.14243/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":"2026-07-05T00:16:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e4zGyRAoO9XHlVt9PHb0oGnZNRztmVQkDk2vLwmsjSy/Qlur6QhYQlf3fCkUDGUBUEoKnvp1pkluHqiR/4b8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:38:46.202092Z"},"content_sha256":"96fbe20a425e631aab3c8503de4c7eb7429cfd5855e49655ee80c5076434c30f","schema_version":"1.0","event_id":"sha256:96fbe20a425e631aab3c8503de4c7eb7429cfd5855e49655ee80c5076434c30f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QSTBSW5V2MKG6KCRRFERE6ND56/bundle.json","state_url":"https://pith.science/pith/QSTBSW5V2MKG6KCRRFERE6ND56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QSTBSW5V2MKG6KCRRFERE6ND56/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":"2026-08-05T08:38:46Z","links":{"resolver":"https://pith.science/pith/QSTBSW5V2MKG6KCRRFERE6ND56","bundle":"https://pith.science/pith/QSTBSW5V2MKG6KCRRFERE6ND56/bundle.json","state":"https://pith.science/pith/QSTBSW5V2MKG6KCRRFERE6ND56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QSTBSW5V2MKG6KCRRFERE6ND56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QSTBSW5V2MKG6KCRRFERE6ND56","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":"6b5e863c4a4b16d2f3067409f13964e226ad7316ea157c8a020cf94ac5eec53f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-10-31T03:56:32Z","title_canon_sha256":"955052a258f190a1ca90655a6ab016d70d30872b67cc902a62a69440e0da393c"},"schema_version":"1.0","source":{"id":"1910.14243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.14243","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"arxiv_version","alias_value":"1910.14243v1","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14243","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"pith_short_12","alias_value":"QSTBSW5V2MKG","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"pith_short_16","alias_value":"QSTBSW5V2MKG6KCR","created_at":"2026-07-05T00:16:08Z"},{"alias_kind":"pith_short_8","alias_value":"QSTBSW5V","created_at":"2026-07-05T00:16:08Z"}],"graph_snapshots":[{"event_id":"sha256:96fbe20a425e631aab3c8503de4c7eb7429cfd5855e49655ee80c5076434c30f","target":"graph","created_at":"2026-07-05T00:16:08Z","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/1910.14243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prediction of language varieties and dialects is an important language processing task, with a wide range of applications. For Arabic, the native tongue of ~ 300 million people, most varieties remain unsupported. To ease this bottleneck, we present a very large scale dataset covering 319 cities from all 21 Arab countries. We introduce a hierarchical attention multi-task learning (HA-MTL) approach for dialect identification exploiting our data at the city, state, and country levels. We also evaluate use of BERT on the three tasks, comparing it to the MTL approach. We benchmark and release our d","authors_text":"AbdelRahim Elmadany, Arun Rajendran, Chiyu Zhang, Lyle Ungar, Muhammad Abdul-Mageed","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-10-31T03:56:32Z","title":"DiaNet: BERT and Hierarchical Attention Multi-Task Learning of Fine-Grained Dialect"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14243","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":"sha256:5581a53a67ff1510565a52c9c1367984b85112fb8670ccf4c6a968e7122819b3","target":"record","created_at":"2026-07-05T00:16:08Z","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":"6b5e863c4a4b16d2f3067409f13964e226ad7316ea157c8a020cf94ac5eec53f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-10-31T03:56:32Z","title_canon_sha256":"955052a258f190a1ca90655a6ab016d70d30872b67cc902a62a69440e0da393c"},"schema_version":"1.0","source":{"id":"1910.14243","kind":"arxiv","version":1}},"canonical_sha256":"84a6195bb5d3146f285189491279a3efb9ce31ac974ba06ea94f71124ef5f59b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84a6195bb5d3146f285189491279a3efb9ce31ac974ba06ea94f71124ef5f59b","first_computed_at":"2026-07-05T00:16:08.971105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:08.971105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dk8jZtRr5bU9g9sDCgjA/iwazKSSUZQSJ6SN3Am/Pd6u1EYj0GpUD4UJLhm8WPN/vmuG0oySbkWPIutf0/vMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:08.971520Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.14243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5581a53a67ff1510565a52c9c1367984b85112fb8670ccf4c6a968e7122819b3","sha256:96fbe20a425e631aab3c8503de4c7eb7429cfd5855e49655ee80c5076434c30f"],"state_sha256":"dc217018b296908faaf6b1842cd08e25e20ac0d4005bee7bdfd0258649cc7094"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGWAmFQ+H6HCT096nQ6jUO7bCUGMbEU32wWa0rdx+tFyzO+pZt1iRoZgy0cP0aYIOIQh2+9F3vQ3rPnaA6i0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:38:46.205911Z","bundle_sha256":"528c646085531927ae3c081b03cfe27e8838aad17c8b8ac11af1692f6c5ee0f9"}}