{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:Y5QLVAJLHRXQ2V25JN7KGKAIAS","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":"2589aeb607708c71d631fd08ca433cbface50aefe64f82c8d6333052e096ace8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-29T18:27:43Z","title_canon_sha256":"661c7dc934475c4a8944fee5bc9bbf70291043947c786d7a30eaf720fa30230a"},"schema_version":"1.0","source":{"id":"1804.10974","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10974","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10974v1","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10974","created_at":"2026-05-18T00:17:15Z"},{"alias_kind":"pith_short_12","alias_value":"Y5QLVAJLHRXQ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"Y5QLVAJLHRXQ2V25","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"Y5QLVAJL","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:a2ccc934d956010ed28eb292e98b07d8a6800d995cd387adb17b20389f8d057e","target":"graph","created_at":"2026-05-18T00:17:15Z","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":"In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counterpart of RAML and the entropy regularized reinforcement learning. Inspired by the connection, we propose two sequence prediction algorithms, one extending RAML with fine-grained credit assignment and the other improving Actor-Critic with a systematic entropy regularization. On two benchmark datasets, we show the proposed algorithms outperform RAML and Actor-Critic respectively, providing new alternatives to sequence p","authors_text":"Eduard Hovy, Qizhe Xie, Zihang Dai","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-29T18:27:43Z","title":"From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10974","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":"sha256:2fd321a4e8be8f4cc3a1a2bc46100811c6a93804b29193b7d73f9d8cb92a8a2c","target":"record","created_at":"2026-05-18T00:17:15Z","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":"2589aeb607708c71d631fd08ca433cbface50aefe64f82c8d6333052e096ace8","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-29T18:27:43Z","title_canon_sha256":"661c7dc934475c4a8944fee5bc9bbf70291043947c786d7a30eaf720fa30230a"},"schema_version":"1.0","source":{"id":"1804.10974","kind":"arxiv","version":1}},"canonical_sha256":"c760ba812b3c6f0d575d4b7ea3280804a939ef76fd227d6608a2eff8c8405584","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c760ba812b3c6f0d575d4b7ea3280804a939ef76fd227d6608a2eff8c8405584","first_computed_at":"2026-05-18T00:17:15.019313Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:15.019313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LEbpWDHAmw5WEo3zIzSuheFD8zFiO12/DRu7IH13Or8PgFJFzR63zdCOIYbr0EToZWlfGo/cam9yVudyg42QCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:15.020000Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.10974","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2fd321a4e8be8f4cc3a1a2bc46100811c6a93804b29193b7d73f9d8cb92a8a2c","sha256:a2ccc934d956010ed28eb292e98b07d8a6800d995cd387adb17b20389f8d057e"],"state_sha256":"86e2d5876d49603d2d5fab692857e363d8d021dc3da88474a88dab0dcf43d4de"}