{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RM3IPZ72WLDYHYNI24HJSF2MDV","short_pith_number":"pith:RM3IPZ72","canonical_record":{"source":{"id":"2504.10160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T12:14:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"baec9f5d9b3f939ed32852bdb44bf507ca60b0967dfbbc5441f820f47ed3eb97","abstract_canon_sha256":"4a47eb2a24b3b42a78d2c5ffb1ecc22ed290c395b549cbb8e0d9790f7a8b8b61"},"schema_version":"1.0"},"canonical_sha256":"8b3687e7fab2c783e1a8d70e99174c1d5a14c712ef00fdcac5e9d28f6ad2dd1e","source":{"kind":"arxiv","id":"2504.10160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10160","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10160v1","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10160","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"RM3IPZ72WLDY","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"RM3IPZ72WLDYHYNI","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"RM3IPZ72","created_at":"2026-07-05T10:48:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RM3IPZ72WLDYHYNI24HJSF2MDV","target":"record","payload":{"canonical_record":{"source":{"id":"2504.10160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T12:14:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"baec9f5d9b3f939ed32852bdb44bf507ca60b0967dfbbc5441f820f47ed3eb97","abstract_canon_sha256":"4a47eb2a24b3b42a78d2c5ffb1ecc22ed290c395b549cbb8e0d9790f7a8b8b61"},"schema_version":"1.0"},"canonical_sha256":"8b3687e7fab2c783e1a8d70e99174c1d5a14c712ef00fdcac5e9d28f6ad2dd1e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:48.504517Z","signature_b64":"9D9oSQrdAhKaQQTbvCCktAahpdzoLsKTmJf/pBnUn0Jq74v7hry/PakTfO4/xEkbXdz1PAqHaQt2231TJXM/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3687e7fab2c783e1a8d70e99174c1d5a14c712ef00fdcac5e9d28f6ad2dd1e","last_reissued_at":"2026-07-05T10:48:48.504029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:48.504029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.10160","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zgei1JwqyBqffJUClR+TAAsWx0ePxHE+Y+iHxKFckU8Cr1fhSBiIq6NFBxDAux41UJ56zVJnIoDct1b7HZV3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:13:38.294817Z"},"content_sha256":"a3741a08b4bc4496abaced836df50b474c68125a6d42d0fc5c5cefc2390b1bc9","schema_version":"1.0","event_id":"sha256:a3741a08b4bc4496abaced836df50b474c68125a6d42d0fc5c5cefc2390b1bc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RM3IPZ72WLDYHYNI24HJSF2MDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiahan Ren, Jian Wu, Jiayuan Su, Ruizhe Chen, Shaosheng Cao, Yan Zhang, Yao Hu, Zhaopeng Feng, Zhe Xu, Zuozhu Liu","submitted_at":"2025-04-14T12:14:18Z","abstract_excerpt":"Large-scale reinforcement learning (RL) methods have proven highly effective in enhancing the reasoning abilities of large language models (LLMs), particularly for tasks with verifiable solutions such as mathematics and coding. However, applying this idea to machine translation (MT), where outputs are flexibly formatted and difficult to automatically evaluate with explicit rules, remains underexplored. In this work, we introduce MT-R1-Zero, the first open-source adaptation of the R1-Zero RL framework for MT without supervised fine-tuning or cold-start. We propose a rule-metric mixed reward mec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10160","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.10160/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":"2026-07-05T10:48:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FhOSz391a7J+NDTryme7tP6DzL6n8quQA6ujIN3Xq+FNucMGwLseASsR47pSxUVcoIOWskiztwZosmx3+0RwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:13:38.295181Z"},"content_sha256":"7c0e9159bb41c65ba30aec622a6ca49c5d9c1a030725d4402abbbb88946dd4d4","schema_version":"1.0","event_id":"sha256:7c0e9159bb41c65ba30aec622a6ca49c5d9c1a030725d4402abbbb88946dd4d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RM3IPZ72WLDYHYNI24HJSF2MDV/bundle.json","state_url":"https://pith.science/pith/RM3IPZ72WLDYHYNI24HJSF2MDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RM3IPZ72WLDYHYNI24HJSF2MDV/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":"2026-07-06T23:13:38Z","links":{"resolver":"https://pith.science/pith/RM3IPZ72WLDYHYNI24HJSF2MDV","bundle":"https://pith.science/pith/RM3IPZ72WLDYHYNI24HJSF2MDV/bundle.json","state":"https://pith.science/pith/RM3IPZ72WLDYHYNI24HJSF2MDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RM3IPZ72WLDYHYNI24HJSF2MDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RM3IPZ72WLDYHYNI24HJSF2MDV","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":"4a47eb2a24b3b42a78d2c5ffb1ecc22ed290c395b549cbb8e0d9790f7a8b8b61","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T12:14:18Z","title_canon_sha256":"baec9f5d9b3f939ed32852bdb44bf507ca60b0967dfbbc5441f820f47ed3eb97"},"schema_version":"1.0","source":{"id":"2504.10160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10160","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10160v1","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10160","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"RM3IPZ72WLDY","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"RM3IPZ72WLDYHYNI","created_at":"2026-07-05T10:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"RM3IPZ72","created_at":"2026-07-05T10:48:48Z"}],"graph_snapshots":[{"event_id":"sha256:7c0e9159bb41c65ba30aec622a6ca49c5d9c1a030725d4402abbbb88946dd4d4","target":"graph","created_at":"2026-07-05T10:48:48Z","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/2504.10160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale reinforcement learning (RL) methods have proven highly effective in enhancing the reasoning abilities of large language models (LLMs), particularly for tasks with verifiable solutions such as mathematics and coding. However, applying this idea to machine translation (MT), where outputs are flexibly formatted and difficult to automatically evaluate with explicit rules, remains underexplored. In this work, we introduce MT-R1-Zero, the first open-source adaptation of the R1-Zero RL framework for MT without supervised fine-tuning or cold-start. We propose a rule-metric mixed reward mec","authors_text":"Jiahan Ren, Jian Wu, Jiayuan Su, Ruizhe Chen, Shaosheng Cao, Yan Zhang, Yao Hu, Zhaopeng Feng, Zhe Xu, Zuozhu Liu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T12:14:18Z","title":"MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10160","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:a3741a08b4bc4496abaced836df50b474c68125a6d42d0fc5c5cefc2390b1bc9","target":"record","created_at":"2026-07-05T10:48:48Z","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":"4a47eb2a24b3b42a78d2c5ffb1ecc22ed290c395b549cbb8e0d9790f7a8b8b61","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-14T12:14:18Z","title_canon_sha256":"baec9f5d9b3f939ed32852bdb44bf507ca60b0967dfbbc5441f820f47ed3eb97"},"schema_version":"1.0","source":{"id":"2504.10160","kind":"arxiv","version":1}},"canonical_sha256":"8b3687e7fab2c783e1a8d70e99174c1d5a14c712ef00fdcac5e9d28f6ad2dd1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b3687e7fab2c783e1a8d70e99174c1d5a14c712ef00fdcac5e9d28f6ad2dd1e","first_computed_at":"2026-07-05T10:48:48.504029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:48.504029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9D9oSQrdAhKaQQTbvCCktAahpdzoLsKTmJf/pBnUn0Jq74v7hry/PakTfO4/xEkbXdz1PAqHaQt2231TJXM/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:48.504517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3741a08b4bc4496abaced836df50b474c68125a6d42d0fc5c5cefc2390b1bc9","sha256:7c0e9159bb41c65ba30aec622a6ca49c5d9c1a030725d4402abbbb88946dd4d4"],"state_sha256":"49e3f626bba7ef8c5507df7367093f87b869f6faba98220caa82d168081235cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KsbTnneXpdVl+ieaN4GthwFIqrXkmDsqi8qF5udYVoSf16zdYxJQz7Yhb9wUzyg+N0BErDmVekN07TWkmEGVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:13:38.297621Z","bundle_sha256":"0971a1d276393f4bc685a7d816c9296cc6937f1c7c898fe6f5d48535972f8f0d"}}