{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:3HNZ3IAXCRLOI57EXEKF7WHH4G","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":"d12c285df358cb977656e53277b69a4371de5c9474044ccb43e149a5042d8012","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:25:54Z","title_canon_sha256":"3a4cbd6b13b46c7ac1cc6b4b3d15f79ba5486d69f20f6c201ed15e149f623804"},"schema_version":"1.0","source":{"id":"1511.06732","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06732","created_at":"2026-05-18T01:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06732v7","created_at":"2026-05-18T01:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06732","created_at":"2026-05-18T01:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"3HNZ3IAXCRLO","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"3HNZ3IAXCRLOI57E","created_at":"2026-05-18T12:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"3HNZ3IAX","created_at":"2026-05-18T12:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:217f0ef335c74e85fcc28535d8a9b2594b936220ab0234b1cb2d5a4dd11dcd38","target":"graph","created_at":"2026-05-18T01:15:23Z","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":"Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some context such as an image. However, at test time the model is expected to generate the entire sequence from scratch. This discrepancy makes generation brittle, as errors may accumulate along the way. We address this issue by proposing a novel sequence level training algorithm that directly optimizes the metric used at test time, such as BLEU or ROUGE. On three different tasks, our approach outperforms sev","authors_text":"Marc'Aurelio Ranzato, Michael Auli, Sumit Chopra, Wojciech Zaremba","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:25:54Z","title":"Sequence Level Training with Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06732","kind":"arxiv","version":7},"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:a5b4136eaa564cbbd71d4dc256e4dc48342dc2edd77900e5f2e3731645378f04","target":"record","created_at":"2026-05-18T01:15:23Z","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":"d12c285df358cb977656e53277b69a4371de5c9474044ccb43e149a5042d8012","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:25:54Z","title_canon_sha256":"3a4cbd6b13b46c7ac1cc6b4b3d15f79ba5486d69f20f6c201ed15e149f623804"},"schema_version":"1.0","source":{"id":"1511.06732","kind":"arxiv","version":7}},"canonical_sha256":"d9db9da0171456e477e4b9145fd8e7e1bf62bd3bfbb93c99b0d08188356527a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9db9da0171456e477e4b9145fd8e7e1bf62bd3bfbb93c99b0d08188356527a8","first_computed_at":"2026-05-18T01:15:23.043277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:23.043277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5LZansffQoU3+X0nUfz/gTKoXXNPSAUOqpVXyJjLFeuU/08Ks5Uc3wo8aAidoSrjQiPnP4gKPyKEdox1PwoEBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:23.043940Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06732","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5b4136eaa564cbbd71d4dc256e4dc48342dc2edd77900e5f2e3731645378f04","sha256:217f0ef335c74e85fcc28535d8a9b2594b936220ab0234b1cb2d5a4dd11dcd38"],"state_sha256":"fa5aa5ebc15c2f024d64ed22d414bfe4ae50106a92035c2d2ee3cdb4ad2be7c1"}