{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RHS44BZDYARKHSAYY4633NBE6B","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":"9304d93622cbcfb15195b036255681d38a4e67f1b54bfbb06aeb769e2ea1b5c1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T14:52:15Z","title_canon_sha256":"41d9160e2ffbd3ef05d62bc617f2ca4fb7d7459a63d1e45592097dfe489996ef"},"schema_version":"1.0","source":{"id":"2012.15178","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15178","created_at":"2026-07-05T02:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15178v1","created_at":"2026-07-05T02:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15178","created_at":"2026-07-05T02:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"RHS44BZDYARK","created_at":"2026-07-05T02:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"RHS44BZDYARKHSAY","created_at":"2026-07-05T02:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"RHS44BZD","created_at":"2026-07-05T02:03:05Z"}],"graph_snapshots":[{"event_id":"sha256:093ddf95be519b586f2c9d792f6f57c3ad3903c42dbf83d4ba261f3b63b66218","target":"graph","created_at":"2026-07-05T02:03:05Z","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/2012.15178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural machine translation (NMT) is typically domain-dependent and style-dependent, and it requires lots of training data. State-of-the-art NMT models often fall short in handling colloquial variations of its source language and the lack of parallel data in this regard is a challenging hurdle in systematically improving the existing models. In this work, we develop a novel colloquial Indonesian-English test-set collected from YouTube transcript and Twitter. We perform synthetic style augmentation to the source of formal Indonesian language and show that it improves the baseline Id-En models (i","authors_text":"Alham Fikri Aji, Asrul Sani Ariesandy, Mukhlis Amien, Radityo Eko Prasojo","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T14:52:15Z","title":"Synthetic Source Language Augmentation for Colloquial Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15178","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":"sha256:569e04c22f52010944ed63363d5e735b5e96581995ae6985bda30e8f0146d5ee","target":"record","created_at":"2026-07-05T02:03:05Z","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":"9304d93622cbcfb15195b036255681d38a4e67f1b54bfbb06aeb769e2ea1b5c1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-30T14:52:15Z","title_canon_sha256":"41d9160e2ffbd3ef05d62bc617f2ca4fb7d7459a63d1e45592097dfe489996ef"},"schema_version":"1.0","source":{"id":"2012.15178","kind":"arxiv","version":1}},"canonical_sha256":"89e5ce0723c022a3c818c73dbdb424f0760aeb1d2dc92b17592f28acf70be0dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89e5ce0723c022a3c818c73dbdb424f0760aeb1d2dc92b17592f28acf70be0dc","first_computed_at":"2026-07-05T02:03:05.478770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:03:05.478770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zTegB/u48Pf1bEuCkgJJZ9exDldPDweRKY/lcdqtofKDvZTMCw+nY+fVYbhkPyFc+zpDOf4szdRuHRO/BF1nAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:03:05.479149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15178","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:569e04c22f52010944ed63363d5e735b5e96581995ae6985bda30e8f0146d5ee","sha256:093ddf95be519b586f2c9d792f6f57c3ad3903c42dbf83d4ba261f3b63b66218"],"state_sha256":"8a5472cd74843f6a1ab05bfe96cc55fd2699e43e3b1d68e945e6c9175566a5f3"}