{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4OIBITMFTXJTVDQ4JUJHKQ7QSC","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":"a4747504f5078b63dff8c3e1eb80746f7897a4393da876c1df98fd44dfa6b944","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:16:20Z","title_canon_sha256":"db1d9beadbb813805581eb54bbf58e18c0d878ecc4ac60d4ba398e25765585c2"},"schema_version":"1.0","source":{"id":"1908.08399","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08399","created_at":"2026-07-05T02:32:43Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08399v2","created_at":"2026-07-05T02:32:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08399","created_at":"2026-07-05T02:32:43Z"},{"alias_kind":"pith_short_12","alias_value":"4OIBITMFTXJT","created_at":"2026-07-05T02:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"4OIBITMFTXJTVDQ4","created_at":"2026-07-05T02:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"4OIBITMF","created_at":"2026-07-05T02:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:c6f0d6657ee720240632514a9d48d4bfbc3cb969a67eecbe65a96e3627911a86","target":"graph","created_at":"2026-07-05T02:32:43Z","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/1908.08399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In sequence prediction tasks like neural machine translation, training with cross-entropy loss often leads to models that overgeneralize and plunge into local optima. In this paper, we propose an extended loss function called \\emph{dual skew divergence} (DSD) that integrates two symmetric terms on KL divergences with a balanced weight. We empirically discovered that such a balanced weight plays a crucial role in applying the proposed DSD loss into deep models. Thus we eventually develop a controllable DSD loss for general-purpose scenarios. Our experiments indicate that switching to the DSD lo","authors_text":"Fengshun Xiao, Hai Zhao, Shu Jiang, Yingting Wu, Zuchao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:16:20Z","title":"Controllable Dual Skew Divergence Loss for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08399","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":"sha256:5e5bddfe785b42d4d3f91437b86dd2b80725c3b952201472e8c2797c3d1015cb","target":"record","created_at":"2026-07-05T02:32:43Z","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":"a4747504f5078b63dff8c3e1eb80746f7897a4393da876c1df98fd44dfa6b944","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-22T14:16:20Z","title_canon_sha256":"db1d9beadbb813805581eb54bbf58e18c0d878ecc4ac60d4ba398e25765585c2"},"schema_version":"1.0","source":{"id":"1908.08399","kind":"arxiv","version":2}},"canonical_sha256":"e390144d859dd33a8e1c4d127543f090a19f4d9cdc02e5dcbc1f024cb98ced53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e390144d859dd33a8e1c4d127543f090a19f4d9cdc02e5dcbc1f024cb98ced53","first_computed_at":"2026-07-05T02:32:43.907289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:43.907289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/Un6B9/gWZ+nZY7obchUB0cT0HtA978CLroTZB3WOE3cXdKftpEk9b6z3iY4foK/VitsbL35VF6LfE7BptJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:43.907730Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08399","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e5bddfe785b42d4d3f91437b86dd2b80725c3b952201472e8c2797c3d1015cb","sha256:c6f0d6657ee720240632514a9d48d4bfbc3cb969a67eecbe65a96e3627911a86"],"state_sha256":"483b75e18d2218c89c583c5644d5c7bbe22aed31a75249b99edd07c86cb20216"}