{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GMITAJUJJ5HEDENMOYAIOWG7EF","short_pith_number":"pith:GMITAJUJ","canonical_record":{"source":{"id":"2110.13658","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-26T14:59:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0f210242ae5592fa466b7aa819e3068c597c30f8e9611ffc98879cd11555d0d","abstract_canon_sha256":"6297f2a396fc8df556dd96dec050f5ed022ab7896c6680b8a7f99b625078b858"},"schema_version":"1.0"},"canonical_sha256":"33113026894f4e4191ac76008758df21437248436baee90cd931f254da639e22","source":{"kind":"arxiv","id":"2110.13658","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13658","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13658v2","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13658","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"GMITAJUJJ5HE","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"GMITAJUJJ5HEDENM","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"GMITAJUJ","created_at":"2026-07-05T11:14:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GMITAJUJJ5HEDENMOYAIOWG7EF","target":"record","payload":{"canonical_record":{"source":{"id":"2110.13658","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-26T14:59:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0f210242ae5592fa466b7aa819e3068c597c30f8e9611ffc98879cd11555d0d","abstract_canon_sha256":"6297f2a396fc8df556dd96dec050f5ed022ab7896c6680b8a7f99b625078b858"},"schema_version":"1.0"},"canonical_sha256":"33113026894f4e4191ac76008758df21437248436baee90cd931f254da639e22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:44.633213Z","signature_b64":"F7/ig4RyUxXI1N33KzjIVLc16FI0X8expjArNSYIoNKSA5GDyXAbvTEhwuYxjT5QhgdRhutmS+x3ux5+RiPYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33113026894f4e4191ac76008758df21437248436baee90cd931f254da639e22","last_reissued_at":"2026-07-05T11:14:44.632852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:44.632852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.13658","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"huJ3ch4w2goMMGaAgmxqpN0uO0T/E6dAZOBXRnLZkvqTXFsagQHKYaNjvsUTqJsPjAycZvRqOUG6AcOx7f+ZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:37:12.922012Z"},"content_sha256":"e269f8162b3b6bdc71eb47eb1f9f08043c03eb3a9a8b14675b171ba0357d4e77","schema_version":"1.0","event_id":"sha256:e269f8162b3b6bdc71eb47eb1f9f08043c03eb3a9a8b14675b171ba0357d4e77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GMITAJUJJ5HEDENMOYAIOWG7EF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Arij Riabi, Beno\\^it Sagot, Djam\\'e Seddah","submitted_at":"2021-10-26T14:59:16Z","abstract_excerpt":"Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high-resource languages. Building language models and, more generally, NLP systems for non-standardized and low-resource languages remains a challenging task. In this work, we focus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data displaying a high level of variability, we compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13658","kind":"arxiv","version":2},"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/2110.13658/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":"2026-07-05T11:14:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lTsoo6r3yRIIQ1PXfD9mGnvua5+K/+3zksbOau7SCpAdjLxUIW7zcIBYgAfSazsK/mocWeSCbI6TmISTUJtfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T19:37:12.922944Z"},"content_sha256":"896409eeb2e295b5a5515433630f369145b4c5fad39cf0560a26763915e6493c","schema_version":"1.0","event_id":"sha256:896409eeb2e295b5a5515433630f369145b4c5fad39cf0560a26763915e6493c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMITAJUJJ5HEDENMOYAIOWG7EF/bundle.json","state_url":"https://pith.science/pith/GMITAJUJJ5HEDENMOYAIOWG7EF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMITAJUJJ5HEDENMOYAIOWG7EF/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":"2026-08-17T19:37:12Z","links":{"resolver":"https://pith.science/pith/GMITAJUJJ5HEDENMOYAIOWG7EF","bundle":"https://pith.science/pith/GMITAJUJJ5HEDENMOYAIOWG7EF/bundle.json","state":"https://pith.science/pith/GMITAJUJJ5HEDENMOYAIOWG7EF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMITAJUJJ5HEDENMOYAIOWG7EF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GMITAJUJJ5HEDENMOYAIOWG7EF","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":"6297f2a396fc8df556dd96dec050f5ed022ab7896c6680b8a7f99b625078b858","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-26T14:59:16Z","title_canon_sha256":"c0f210242ae5592fa466b7aa819e3068c597c30f8e9611ffc98879cd11555d0d"},"schema_version":"1.0","source":{"id":"2110.13658","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.13658","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"arxiv_version","alias_value":"2110.13658v2","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.13658","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"pith_short_12","alias_value":"GMITAJUJJ5HE","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"pith_short_16","alias_value":"GMITAJUJJ5HEDENM","created_at":"2026-07-05T11:14:44Z"},{"alias_kind":"pith_short_8","alias_value":"GMITAJUJ","created_at":"2026-07-05T11:14:44Z"}],"graph_snapshots":[{"event_id":"sha256:896409eeb2e295b5a5515433630f369145b4c5fad39cf0560a26763915e6493c","target":"graph","created_at":"2026-07-05T11:14:44Z","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/2110.13658/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent impressive improvements in NLP, largely based on the success of contextual neural language models, have been mostly demonstrated on at most a couple dozen high-resource languages. Building language models and, more generally, NLP systems for non-standardized and low-resource languages remains a challenging task. In this work, we focus on North-African colloquial dialectal Arabic written using an extension of the Latin script, called NArabizi, found mostly on social media and messaging communication. In this low-resource scenario with data displaying a high level of variability, we compa","authors_text":"Arij Riabi, Beno\\^it Sagot, Djam\\'e Seddah","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-26T14:59:16Z","title":"Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.13658","kind":"arxiv","version":2},"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:e269f8162b3b6bdc71eb47eb1f9f08043c03eb3a9a8b14675b171ba0357d4e77","target":"record","created_at":"2026-07-05T11:14:44Z","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":"6297f2a396fc8df556dd96dec050f5ed022ab7896c6680b8a7f99b625078b858","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-26T14:59:16Z","title_canon_sha256":"c0f210242ae5592fa466b7aa819e3068c597c30f8e9611ffc98879cd11555d0d"},"schema_version":"1.0","source":{"id":"2110.13658","kind":"arxiv","version":2}},"canonical_sha256":"33113026894f4e4191ac76008758df21437248436baee90cd931f254da639e22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33113026894f4e4191ac76008758df21437248436baee90cd931f254da639e22","first_computed_at":"2026-07-05T11:14:44.632852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:44.632852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F7/ig4RyUxXI1N33KzjIVLc16FI0X8expjArNSYIoNKSA5GDyXAbvTEhwuYxjT5QhgdRhutmS+x3ux5+RiPYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:44.633213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.13658","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e269f8162b3b6bdc71eb47eb1f9f08043c03eb3a9a8b14675b171ba0357d4e77","sha256:896409eeb2e295b5a5515433630f369145b4c5fad39cf0560a26763915e6493c"],"state_sha256":"dbb49369c2a210f79fd4f84b50363bdb3aecd242f036d0648b501a8aede97ad9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ym5S0f1uSYV9WWXN/jRSgJLkp3e2T/eFwsyOeYdF+EtGf1DkwSuCQAbkOJENEpn8fDRH3T8QmrHkFd1StxI1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T19:37:12.930968Z","bundle_sha256":"f4360a3a26f336bc3dd8bb9b885d0dea6ab41d5ef3a480163ad500ddb2d11946"}}