{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CHIZYBFICH7GVRFXL74RP74OJX","short_pith_number":"pith:CHIZYBFI","canonical_record":{"source":{"id":"1809.01962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T13:12:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de88f4430d78ca5e009ba8d92f7d2e499ef696e625e2c7bc712fa1cdfafb9744","abstract_canon_sha256":"f3c510451e7e5bb901606b6abbec65f3a4cb9fce008b746b3021c2b28f17907e"},"schema_version":"1.0"},"canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","source":{"kind":"arxiv","id":"1809.01962","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CHIZYBFICH7GVRFXL74RP74OJX","target":"record","payload":{"canonical_record":{"source":{"id":"1809.01962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T13:12:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de88f4430d78ca5e009ba8d92f7d2e499ef696e625e2c7bc712fa1cdfafb9744","abstract_canon_sha256":"f3c510451e7e5bb901606b6abbec65f3a4cb9fce008b746b3021c2b28f17907e"},"schema_version":"1.0"},"canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:21.604957Z","signature_b64":"fHK21lWG5Zi7IvDt8ucTx11S2XekzWKjW7XuT+zQ1PXS9PHfXwGjtCgnT6T3MR2WTmbbhO1g4utTP/RV5fGTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","last_reissued_at":"2026-05-18T00:06:21.604545Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:21.604545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.01962","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":"2026-05-18T00:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"On13VL76cnddYvkS39bIrUy4pTRGzNICs+XhpbKVopTi1OAkhtX1nSF9yg9B3Zif3e72tZnjGcbp2nbjkI6KCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:36:03.853625Z"},"content_sha256":"c8878944d0012ae3f13cca97c15c89547023016801252407c128e4c838ead1ec","schema_version":"1.0","event_id":"sha256:c8878944d0012ae3f13cca97c15c89547023016801252407c128e4c838ead1ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CHIZYBFICH7GVRFXL74RP74OJX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Code-switched Language Models Using Dual RNNs and Same-Source Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Preethi Jyothi, Saurabh Garg, Tanmay Parekh","submitted_at":"2018-09-06T13:12:27Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01962","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":""},"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":"2026-05-18T00:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"46Gp784SDOVx4oUqNJy/uz9cem4+Rjbqp6/Lp8J/CQ2GsNRLASO+Xfrc31r/vLpP/VqcPNzqZzYeAbPNWHaXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:36:03.854247Z"},"content_sha256":"691f596c2ffaeb7d5605be20ba5c5d88e45bb492fd99cae3c0a0b7bf5c639997","schema_version":"1.0","event_id":"sha256:691f596c2ffaeb7d5605be20ba5c5d88e45bb492fd99cae3c0a0b7bf5c639997"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/bundle.json","state_url":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CHIZYBFICH7GVRFXL74RP74OJX/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":"2026-05-26T11:36:03Z","links":{"resolver":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX","bundle":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/bundle.json","state":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CHIZYBFICH7GVRFXL74RP74OJX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQoyjzadGWmyqU9yXSJdwZarmnZZ4jeCsB4Ut9bwlx2OT4RizZYT0y87a0PmMMBJPPIT4H+r6G1zx0+j8qq3AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:36:03.857585Z","bundle_sha256":"b763e083f18b96180d9d9e5f8c735db997db5f480f2b0df10072e7a5d89813c2"}}