{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CHIZYBFICH7GVRFXL74RP74OJX","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":"f3c510451e7e5bb901606b6abbec65f3a4cb9fce008b746b3021c2b28f17907e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T13:12:27Z","title_canon_sha256":"de88f4430d78ca5e009ba8d92f7d2e499ef696e625e2c7bc712fa1cdfafb9744"},"schema_version":"1.0","source":{"id":"1809.01962","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01962","created_at":"2026-05-18T00:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01962v1","created_at":"2026-05-18T00:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01962","created_at":"2026-05-18T00:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"CHIZYBFICH7G","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CHIZYBFICH7GVRFX","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CHIZYBFI","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:691f596c2ffaeb7d5605be20ba5c5d88e45bb492fd99cae3c0a0b7bf5c639997","target":"graph","created_at":"2026-05-18T00:06:21Z","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"},"paper":{"abstract_excerpt":"This work focuses on building language models (LMs) for code-switched text. We propose two techniques that significantly improve these LMs: 1) A novel recurrent neural network unit with dual components that focus on each language in the code-switched text separately 2) Pretraining the LM using synthetic text from a generative model estimated using the training data. We demonstrate the effectiveness of our proposed techniques by reporting perplexities on a Mandarin-English task and derive significant reductions in perplexity.","authors_text":"Preethi Jyothi, Saurabh Garg, Tanmay Parekh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T13:12:27Z","title":"Code-switched Language Models Using Dual RNNs and Same-Source Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01962","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:c8878944d0012ae3f13cca97c15c89547023016801252407c128e4c838ead1ec","target":"record","created_at":"2026-05-18T00:06:21Z","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":"f3c510451e7e5bb901606b6abbec65f3a4cb9fce008b746b3021c2b28f17907e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T13:12:27Z","title_canon_sha256":"de88f4430d78ca5e009ba8d92f7d2e499ef696e625e2c7bc712fa1cdfafb9744"},"schema_version":"1.0","source":{"id":"1809.01962","kind":"arxiv","version":1}},"canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","first_computed_at":"2026-05-18T00:06:21.604545Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:21.604545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fHK21lWG5Zi7IvDt8ucTx11S2XekzWKjW7XuT+zQ1PXS9PHfXwGjtCgnT6T3MR2WTmbbhO1g4utTP/RV5fGTCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:21.604957Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.01962","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8878944d0012ae3f13cca97c15c89547023016801252407c128e4c838ead1ec","sha256:691f596c2ffaeb7d5605be20ba5c5d88e45bb492fd99cae3c0a0b7bf5c639997"],"state_sha256":"c2851659b2192b0bf93622a6a1fe6b1c142b06757189dbf5461f65d9e83a02b1"}