{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DAA4YGRJS4TMQU7DWKJYAJWCKH","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":"4b57d2c2a16b4c2dbeffc4a89cb1625b6f82444aeed5d1abaf18e3c3ab62816b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T01:59:58Z","title_canon_sha256":"7c18591af2f234e9d9b8f135b79bd650049fd0b4d809e81d27740875c711b2b0"},"schema_version":"1.0","source":{"id":"2505.20622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20622","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20622v1","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20622","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"DAA4YGRJS4TM","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"DAA4YGRJS4TMQU7D","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"DAA4YGRJ","created_at":"2026-07-05T11:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:d3db3549c73bfd66dad6c5718f121691931c4e611fc372f25636adbc0469dada","target":"graph","created_at":"2026-07-05T11:10:15Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.20622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Sequential Policy Optimization for Simultaneous Machine Translation (SeqPO-SiMT), a new policy optimization framework that defines the simultaneous machine translation (SiMT) task as a sequential decision making problem, incorporating a tailored reward to enhance translation quality while reducing latency. In contrast to popular Reinforcement Learning from Human Feedback (RLHF) methods, such as PPO and DPO, which are typically applied in single-step tasks, SeqPO-SiMT effectively tackles the multi-step SiMT task. This intuitive framework allows the SiMT LLMs to simulate and refine th","authors_text":"Jiankai Sun, Shanbo Cheng, Ting Xu, Wai Lam, Zhichao Huang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T01:59:58Z","title":"SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20622","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":"sha256:2e66536a30315024d2fc9043e021686d888b54340b53ced382236bef0ff4275e","target":"record","created_at":"2026-07-05T11:10:15Z","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":"4b57d2c2a16b4c2dbeffc4a89cb1625b6f82444aeed5d1abaf18e3c3ab62816b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-27T01:59:58Z","title_canon_sha256":"7c18591af2f234e9d9b8f135b79bd650049fd0b4d809e81d27740875c711b2b0"},"schema_version":"1.0","source":{"id":"2505.20622","kind":"arxiv","version":1}},"canonical_sha256":"1801cc1a299726c853e3b2938026c251e0ea3696fcb98a1a2610213410ee5949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1801cc1a299726c853e3b2938026c251e0ea3696fcb98a1a2610213410ee5949","first_computed_at":"2026-07-05T11:10:15.571692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:15.571692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EZhtp3Sx+AAocqeTP0pjecaTSAnNwchAEff2nZUjoO07U95URKeYJhoxKKbstmAk7Cc7xxqPBsNzyzviIZ+6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:15.572265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e66536a30315024d2fc9043e021686d888b54340b53ced382236bef0ff4275e","sha256:d3db3549c73bfd66dad6c5718f121691931c4e611fc372f25636adbc0469dada"],"state_sha256":"eb0ce07c11b3b088eab0b4fe1dccd580ffd980bac859ddc587aa0430e1b1f541"}