{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y5QLVAJLHRXQ2V25JN7KGKAIAS","short_pith_number":"pith:Y5QLVAJL","schema_version":"1.0","canonical_sha256":"c760ba812b3c6f0d575d4b7ea3280804a939ef76fd227d6608a2eff8c8405584","source":{"kind":"arxiv","id":"1804.10974","version":1},"attestation_state":"computed","paper":{"title":"From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Eduard Hovy, Qizhe Xie, Zihang Dai","submitted_at":"2018-04-29T18:27:43Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.10974","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-29T18:27:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"661c7dc934475c4a8944fee5bc9bbf70291043947c786d7a30eaf720fa30230a","abstract_canon_sha256":"2589aeb607708c71d631fd08ca433cbface50aefe64f82c8d6333052e096ace8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:15.020000Z","signature_b64":"LEbpWDHAmw5WEo3zIzSuheFD8zFiO12/DRu7IH13Or8PgFJFzR63zdCOIYbr0EToZWlfGo/cam9yVudyg42QCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c760ba812b3c6f0d575d4b7ea3280804a939ef76fd227d6608a2eff8c8405584","last_reissued_at":"2026-05-18T00:17:15.019313Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:15.019313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Eduard Hovy, Qizhe Xie, Zihang Dai","submitted_at":"2018-04-29T18:27:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10974","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.10974","created_at":"2026-05-18T00:17:15.019416+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10974v1","created_at":"2026-05-18T00:17:15.019416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10974","created_at":"2026-05-18T00:17:15.019416+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5QLVAJLHRXQ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5QLVAJLHRXQ2V25","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5QLVAJL","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS","json":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS.json","graph_json":"https://pith.science/api/pith-number/Y5QLVAJLHRXQ2V25JN7KGKAIAS/graph.json","events_json":"https://pith.science/api/pith-number/Y5QLVAJLHRXQ2V25JN7KGKAIAS/events.json","paper":"https://pith.science/paper/Y5QLVAJL"},"agent_actions":{"view_html":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS","download_json":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS.json","view_paper":"https://pith.science/paper/Y5QLVAJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10974&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5QLVAJLHRXQ2V25JN7KGKAIAS/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5QLVAJLHRXQ2V25JN7KGKAIAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS/action/storage_attestation","attest_author":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS/action/author_attestation","sign_citation":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS/action/citation_signature","submit_replication":"https://pith.science/pith/Y5QLVAJLHRXQ2V25JN7KGKAIAS/action/replication_record"}},"created_at":"2026-05-18T00:17:15.019416+00:00","updated_at":"2026-05-18T00:17:15.019416+00:00"}