{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SPKIT5B2MDLZ5UGERO3BKKEFRV","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":"26edfe4cc526b65343cc54d849352ce2cb0aa79d985c39f075e682d7f66c8ef7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T18:50:16Z","title_canon_sha256":"101899b58f7775f56afcc2855718d0c7d1bd973a0b67fedf2a7aa717f30eac7f"},"schema_version":"1.0","source":{"id":"2211.07628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07628","created_at":"2026-07-05T05:15:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07628v1","created_at":"2026-07-05T05:15:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07628","created_at":"2026-07-05T05:15:55Z"},{"alias_kind":"pith_short_12","alias_value":"SPKIT5B2MDLZ","created_at":"2026-07-05T05:15:55Z"},{"alias_kind":"pith_short_16","alias_value":"SPKIT5B2MDLZ5UGE","created_at":"2026-07-05T05:15:55Z"},{"alias_kind":"pith_short_8","alias_value":"SPKIT5B2","created_at":"2026-07-05T05:15:55Z"}],"graph_snapshots":[{"event_id":"sha256:24a25d8543cfe1b19817b63c60847a7aa249f9ee22398e87329a250e1671aca0","target":"graph","created_at":"2026-07-05T05:15:55Z","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/2211.07628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we focus on intrasentential code-mixing and propose several different Synthetic Code-Mixing (SCM) data augmentation methods that outperform the baseline on downstream sentiment analysis tasks across various amounts of labeled gold data. Most importantly, our proposed methods demonstrate that strategically replacing parts of sentences in the matrix language with a constant mask significantly improves classification accuracy, motivating further linguistic insights into the phenomenon of code-mixing. We test our data augmentation method in a variety of low-resource and cross-lingual","authors_text":"Kenton Murray, Shuyue Stella Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T18:50:16Z","title":"Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07628","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":"sha256:7248791a5ed7fcaa6c077152f835ada1d39aa7ca078db9ab49fedb464bcd2610","target":"record","created_at":"2026-07-05T05:15:55Z","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":"26edfe4cc526b65343cc54d849352ce2cb0aa79d985c39f075e682d7f66c8ef7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-14T18:50:16Z","title_canon_sha256":"101899b58f7775f56afcc2855718d0c7d1bd973a0b67fedf2a7aa717f30eac7f"},"schema_version":"1.0","source":{"id":"2211.07628","kind":"arxiv","version":1}},"canonical_sha256":"93d489f43a60d79ed0c48bb61528858d43e03bf0213e905dae44e5222e16d30f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93d489f43a60d79ed0c48bb61528858d43e03bf0213e905dae44e5222e16d30f","first_computed_at":"2026-07-05T05:15:55.629225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:55.629225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dqY9skmSaB9zI+ltg8BWmYUKYhXV5A1FhzpSPRlZeKGQRZsh1UAoit8vjajSZUqN6uZHFRT9336ceR7XxrIdCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:55.629710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7248791a5ed7fcaa6c077152f835ada1d39aa7ca078db9ab49fedb464bcd2610","sha256:24a25d8543cfe1b19817b63c60847a7aa249f9ee22398e87329a250e1671aca0"],"state_sha256":"df86385b7450a7b7b2edc687ff83ec212151942c87269bb5381c8f259cb80030"}