{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IWRJJ2NHGMO3P624ZNZEVOULB7","short_pith_number":"pith:IWRJJ2NH","canonical_record":{"source":{"id":"2505.21816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T22:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"37a43239bf0dda83657653536744812b071900825dc260d22358230dce715402","abstract_canon_sha256":"725e04f69724c5a8f7f1e90af540aaa29bf0c590be69dc5b37c35998b1e155f2"},"schema_version":"1.0"},"canonical_sha256":"45a294e9a7331db7fb5ccb724aba8b0ff5c900f3ad3390adac5359b6c302aeee","source":{"kind":"arxiv","id":"2505.21816","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21816","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21816v1","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21816","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"IWRJJ2NHGMO3","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_16","alias_value":"IWRJJ2NHGMO3P624","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_8","alias_value":"IWRJJ2NH","created_at":"2026-07-05T11:11:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IWRJJ2NHGMO3P624ZNZEVOULB7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.21816","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T22:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"37a43239bf0dda83657653536744812b071900825dc260d22358230dce715402","abstract_canon_sha256":"725e04f69724c5a8f7f1e90af540aaa29bf0c590be69dc5b37c35998b1e155f2"},"schema_version":"1.0"},"canonical_sha256":"45a294e9a7331db7fb5ccb724aba8b0ff5c900f3ad3390adac5359b6c302aeee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:04.044656Z","signature_b64":"t1gb+bGwXyeZeOrm1oERNfjnk8QIf4dmBZSiAj9jnyeBuP4Er4Rm0BudpCsE1gkC6wI/pinelmmU5XXWORXsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45a294e9a7331db7fb5ccb724aba8b0ff5c900f3ad3390adac5359b6c302aeee","last_reissued_at":"2026-07-05T11:11:04.044220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:04.044220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.21816","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":"2026-07-05T11:11:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJ3w/5+0Vlgz75SYX30b1qnFXf/bPhNdGAUBIyhxLA02h1j+0l2xvNS57Kc7HLNUk2jeiUMnhj+eLayXHERGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:42:17.924670Z"},"content_sha256":"28b664bf60f3cc68ccf4ce3f345acffcf15b5bd14d0c0dd290292fc6c37d7a87","schema_version":"1.0","event_id":"sha256:28b664bf60f3cc68ccf4ce3f345acffcf15b5bd14d0c0dd290292fc6c37d7a87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IWRJJ2NHGMO3P624ZNZEVOULB7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Common Assumptions about Arabic Dialects in NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amr Keleg, Sharon Goldwater, Walid Magdy","submitted_at":"2025-05-27T22:56:33Z","abstract_excerpt":"Arabic has diverse dialects, where one dialect can be substantially different from the others. In the NLP literature, some assumptions about these dialects are widely adopted (e.g., ``Arabic dialects can be grouped into distinguishable regional dialects\") and are manifested in different computational tasks such as Arabic Dialect Identification (ADI). However, these assumptions are not quantitatively verified. We identify four of these assumptions and examine them by extending and analyzing a multi-label dataset, where the validity of each sentence in 11 different country-level dialects is manu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21816","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/2505.21816/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":"2026-07-05T11:11:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hypNgS79hewBy0cAVPO5v3ehYjxUqW49KRYpGDRUtbr8miz+VwwGDieQxt9H0MOdflBjuNfWGrpYJ2XHZcDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:42:17.925518Z"},"content_sha256":"d11bcb9e2530bf699b5fd1ea699d5465f471dec22abb507fbb10893e1e2d61f3","schema_version":"1.0","event_id":"sha256:d11bcb9e2530bf699b5fd1ea699d5465f471dec22abb507fbb10893e1e2d61f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWRJJ2NHGMO3P624ZNZEVOULB7/bundle.json","state_url":"https://pith.science/pith/IWRJJ2NHGMO3P624ZNZEVOULB7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWRJJ2NHGMO3P624ZNZEVOULB7/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":"2026-08-08T09:42:17Z","links":{"resolver":"https://pith.science/pith/IWRJJ2NHGMO3P624ZNZEVOULB7","bundle":"https://pith.science/pith/IWRJJ2NHGMO3P624ZNZEVOULB7/bundle.json","state":"https://pith.science/pith/IWRJJ2NHGMO3P624ZNZEVOULB7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWRJJ2NHGMO3P624ZNZEVOULB7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IWRJJ2NHGMO3P624ZNZEVOULB7","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":"725e04f69724c5a8f7f1e90af540aaa29bf0c590be69dc5b37c35998b1e155f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T22:56:33Z","title_canon_sha256":"37a43239bf0dda83657653536744812b071900825dc260d22358230dce715402"},"schema_version":"1.0","source":{"id":"2505.21816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21816","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21816v1","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21816","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_12","alias_value":"IWRJJ2NHGMO3","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_16","alias_value":"IWRJJ2NHGMO3P624","created_at":"2026-07-05T11:11:04Z"},{"alias_kind":"pith_short_8","alias_value":"IWRJJ2NH","created_at":"2026-07-05T11:11:04Z"}],"graph_snapshots":[{"event_id":"sha256:d11bcb9e2530bf699b5fd1ea699d5465f471dec22abb507fbb10893e1e2d61f3","target":"graph","created_at":"2026-07-05T11:11:04Z","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/2505.21816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Arabic has diverse dialects, where one dialect can be substantially different from the others. In the NLP literature, some assumptions about these dialects are widely adopted (e.g., ``Arabic dialects can be grouped into distinguishable regional dialects\") and are manifested in different computational tasks such as Arabic Dialect Identification (ADI). However, these assumptions are not quantitatively verified. We identify four of these assumptions and examine them by extending and analyzing a multi-label dataset, where the validity of each sentence in 11 different country-level dialects is manu","authors_text":"Amr Keleg, Sharon Goldwater, Walid Magdy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T22:56:33Z","title":"Revisiting Common Assumptions about Arabic Dialects in NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21816","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":"sha256:28b664bf60f3cc68ccf4ce3f345acffcf15b5bd14d0c0dd290292fc6c37d7a87","target":"record","created_at":"2026-07-05T11:11:04Z","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":"725e04f69724c5a8f7f1e90af540aaa29bf0c590be69dc5b37c35998b1e155f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T22:56:33Z","title_canon_sha256":"37a43239bf0dda83657653536744812b071900825dc260d22358230dce715402"},"schema_version":"1.0","source":{"id":"2505.21816","kind":"arxiv","version":1}},"canonical_sha256":"45a294e9a7331db7fb5ccb724aba8b0ff5c900f3ad3390adac5359b6c302aeee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45a294e9a7331db7fb5ccb724aba8b0ff5c900f3ad3390adac5359b6c302aeee","first_computed_at":"2026-07-05T11:11:04.044220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:04.044220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t1gb+bGwXyeZeOrm1oERNfjnk8QIf4dmBZSiAj9jnyeBuP4Er4Rm0BudpCsE1gkC6wI/pinelmmU5XXWORXsCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:04.044656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28b664bf60f3cc68ccf4ce3f345acffcf15b5bd14d0c0dd290292fc6c37d7a87","sha256:d11bcb9e2530bf699b5fd1ea699d5465f471dec22abb507fbb10893e1e2d61f3"],"state_sha256":"35784dd84a986444ed529855aea3efe52726a50599c5e3f07bc17aea4c981002"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mnzoQCAzhcn5PmL8wpzIbhg1CYGU2CONdJz7TyfHacp95ZFyOXBCacqFAbLdq/EqSqz44Tv1mA4yOIewgRt8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:42:17.932007Z","bundle_sha256":"ac0874ee17aa22349e01a1439b9fe82786c7ee965de8d764a496c6fd6a65843c"}}