{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:URJVTQFQW7AMJT6F4QQSM6JW4C","short_pith_number":"pith:URJVTQFQ","canonical_record":{"source":{"id":"2506.05070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:18:21Z","cross_cats_sorted":[],"title_canon_sha256":"b4619ef39c237d2ac17e4e57eea6999c6b1e3b57e0248a56b71392039aad7f14","abstract_canon_sha256":"a3a6f7c5f6c0fdf5e7f94fe9d5e187b1ee0b278b39d4392b72f0bb0c3b386ed6"},"schema_version":"1.0"},"canonical_sha256":"a45359c0b0b7c0c4cfc5e421267936e09a1150119ac7a1424b13211558cc7ebc","source":{"kind":"arxiv","id":"2506.05070","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05070","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05070v2","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05070","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"URJVTQFQW7AM","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"URJVTQFQW7AMJT6F","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"URJVTQFQ","created_at":"2026-07-05T11:48:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:URJVTQFQW7AMJT6F4QQSM6JW4C","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05070","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:18:21Z","cross_cats_sorted":[],"title_canon_sha256":"b4619ef39c237d2ac17e4e57eea6999c6b1e3b57e0248a56b71392039aad7f14","abstract_canon_sha256":"a3a6f7c5f6c0fdf5e7f94fe9d5e187b1ee0b278b39d4392b72f0bb0c3b386ed6"},"schema_version":"1.0"},"canonical_sha256":"a45359c0b0b7c0c4cfc5e421267936e09a1150119ac7a1424b13211558cc7ebc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:26.508176Z","signature_b64":"gsKtvFRdHiyu5dv14rnI3UbdRG721Kf/DGBKar2bUQbSfQxFFBhFGeDAVUKeaqRPW23cKA8lTno3xLLy7MuzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a45359c0b0b7c0c4cfc5e421267936e09a1150119ac7a1424b13211558cc7ebc","last_reissued_at":"2026-07-05T11:48:26.507654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:26.507654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05070","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MjYox0JYotxi1/q0zia2t45xg+8pqncfSarmoCHJxFwxzeYifyAWDh3LsUqUQCJfvtSeZG75nIf2OtB2C71lAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:55:10.113214Z"},"content_sha256":"44c997707a52b642511f0e3cfaaf347817b446fc6a290bae99329977031d8036","schema_version":"1.0","event_id":"sha256:44c997707a52b642511f0e3cfaaf347817b446fc6a290bae99329977031d8036"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:URJVTQFQW7AMJT6F4QQSM6JW4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenyu Shi, Jiayin Wang, Mengran Yu, Qiang Zhang, Qi Zhang, Tianjiao Li, Xiaojing Liu, Xuanjing Huang, Yanjun Zhao","submitted_at":"2025-06-05T14:18:21Z","abstract_excerpt":"Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potential. However, we observe that this paradigm performs unexpectedly poorly when applied to colloquial subtitle translation tasks. In this work, we investigate this issue and find that the offline reward model (RM) gradually diverges from the online LLM due to distributional shift, ultimately leading to undesirable training outcomes. To address this, we propose RIVAL, an adversarial training framework that formulates th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05070","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.05070/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:48:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e96CB/mAbqRESsbGm9ZJdrHc+BpoUGL5iVPNmoBDneLnfcr3hKQnf8SksyrL0fwnW+1yYGiGorKyyTXi1LxhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T22:55:10.114238Z"},"content_sha256":"ce1129747b4baba3af75d41c9fcf047ff2a6a0e4346ef5731de22dad7886080f","schema_version":"1.0","event_id":"sha256:ce1129747b4baba3af75d41c9fcf047ff2a6a0e4346ef5731de22dad7886080f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/URJVTQFQW7AMJT6F4QQSM6JW4C/bundle.json","state_url":"https://pith.science/pith/URJVTQFQW7AMJT6F4QQSM6JW4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/URJVTQFQW7AMJT6F4QQSM6JW4C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T22:55:10Z","links":{"resolver":"https://pith.science/pith/URJVTQFQW7AMJT6F4QQSM6JW4C","bundle":"https://pith.science/pith/URJVTQFQW7AMJT6F4QQSM6JW4C/bundle.json","state":"https://pith.science/pith/URJVTQFQW7AMJT6F4QQSM6JW4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/URJVTQFQW7AMJT6F4QQSM6JW4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:URJVTQFQW7AMJT6F4QQSM6JW4C","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":"a3a6f7c5f6c0fdf5e7f94fe9d5e187b1ee0b278b39d4392b72f0bb0c3b386ed6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:18:21Z","title_canon_sha256":"b4619ef39c237d2ac17e4e57eea6999c6b1e3b57e0248a56b71392039aad7f14"},"schema_version":"1.0","source":{"id":"2506.05070","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05070","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05070v2","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05070","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"URJVTQFQW7AM","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"URJVTQFQW7AMJT6F","created_at":"2026-07-05T11:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"URJVTQFQ","created_at":"2026-07-05T11:48:26Z"}],"graph_snapshots":[{"event_id":"sha256:ce1129747b4baba3af75d41c9fcf047ff2a6a0e4346ef5731de22dad7886080f","target":"graph","created_at":"2026-07-05T11:48:26Z","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/2506.05070/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) possess strong multilingual capabilities, and combining Reinforcement Learning from Human Feedback (RLHF) with translation tasks has shown great potential. However, we observe that this paradigm performs unexpectedly poorly when applied to colloquial subtitle translation tasks. In this work, we investigate this issue and find that the offline reward model (RM) gradually diverges from the online LLM due to distributional shift, ultimately leading to undesirable training outcomes. To address this, we propose RIVAL, an adversarial training framework that formulates th","authors_text":"Chenyu Shi, Jiayin Wang, Mengran Yu, Qiang Zhang, Qi Zhang, Tianjiao Li, Xiaojing Liu, Xuanjing Huang, Yanjun Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:18:21Z","title":"RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05070","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":"sha256:44c997707a52b642511f0e3cfaaf347817b446fc6a290bae99329977031d8036","target":"record","created_at":"2026-07-05T11:48:26Z","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":"a3a6f7c5f6c0fdf5e7f94fe9d5e187b1ee0b278b39d4392b72f0bb0c3b386ed6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T14:18:21Z","title_canon_sha256":"b4619ef39c237d2ac17e4e57eea6999c6b1e3b57e0248a56b71392039aad7f14"},"schema_version":"1.0","source":{"id":"2506.05070","kind":"arxiv","version":2}},"canonical_sha256":"a45359c0b0b7c0c4cfc5e421267936e09a1150119ac7a1424b13211558cc7ebc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a45359c0b0b7c0c4cfc5e421267936e09a1150119ac7a1424b13211558cc7ebc","first_computed_at":"2026-07-05T11:48:26.507654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:26.507654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gsKtvFRdHiyu5dv14rnI3UbdRG721Kf/DGBKar2bUQbSfQxFFBhFGeDAVUKeaqRPW23cKA8lTno3xLLy7MuzCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:26.508176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05070","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c997707a52b642511f0e3cfaaf347817b446fc6a290bae99329977031d8036","sha256:ce1129747b4baba3af75d41c9fcf047ff2a6a0e4346ef5731de22dad7886080f"],"state_sha256":"8b3de55e8613c7fe5bd5a74a335c291172c4019438c355101aa51d4f60bd8d22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ETPw8F09ny72bbPB+qQCW/HwkE3dEUpM6IwbFXErbiTSt2o2SfYIMkH08ix2vP4xkhYj5vZCCnrWUSB6doABAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T22:55:10.119520Z","bundle_sha256":"9149ed95f96e6405b652ac9037914052ec4fa302a0f3726de9ae18fb396f59d8"}}