{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7DQUPHZLIWFADHDKU5CN2V3SI7","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":"29334f3190c50f5aa884b47f462683273bf529d06f8f1263dc92943570b5cd9e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T11:30:38Z","title_canon_sha256":"979dab552f258c9edb7ec5e49ece2e4d3197f3ab4a8fc74ef0f3dc64d6da0b5f"},"schema_version":"1.0","source":{"id":"2608.10812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10812","created_at":"2026-08-12T01:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10812v1","created_at":"2026-08-12T01:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10812","created_at":"2026-08-12T01:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"7DQUPHZLIWFA","created_at":"2026-08-12T01:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"7DQUPHZLIWFADHDK","created_at":"2026-08-12T01:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"7DQUPHZL","created_at":"2026-08-12T01:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:052f83881ec2f25ffa5ce66e4a82f663f696e5f18499ce1d3e0b1b530232eca5","target":"graph","created_at":"2026-08-12T01:23:19Z","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/2608.10812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiLMMT-46-v0.1 models, we apply Group Relative Policy Optimization (GRPO) with a reward that averages two reference-free quality estimation models and is gated by language identification. We then linearly interpolate the supervised fine-tuning (SFT) and reinforcement learning (RL) model checkpoints to obtain MiLMMT-46-v1.0. Across 46 languages, the resulting models consistently improve translation quality over their SFT counterparts, outperform stro","authors_text":"Chris Han, Jian Luan, Pei Fu, Pengzhi Gao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T11:30:38Z","title":"Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10812","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":"sha256:0dfb070a355df8bbfc342b3234a4fb7375ad737ddbd98fd448f72429531e8fcc","target":"record","created_at":"2026-08-12T01:23:19Z","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":"29334f3190c50f5aa884b47f462683273bf529d06f8f1263dc92943570b5cd9e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-11T11:30:38Z","title_canon_sha256":"979dab552f258c9edb7ec5e49ece2e4d3197f3ab4a8fc74ef0f3dc64d6da0b5f"},"schema_version":"1.0","source":{"id":"2608.10812","kind":"arxiv","version":1}},"canonical_sha256":"f8e1479f2b458a019c6aa744dd577247d8b760d1776f9e6a0fdf40cd17f79378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8e1479f2b458a019c6aa744dd577247d8b760d1776f9e6a0fdf40cd17f79378","first_computed_at":"2026-08-12T01:23:19.837983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:23:19.837983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p70H7MceUK5/nNwqP6m5Ivau0GIjgqAHpTe42XjWneMo6AIFSCqaauxO3A4mFZDSLjkN2PpcsBwGefi/D6cyDA==","signature_status":"signed_v1","signed_at":"2026-08-12T01:23:19.839710Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0dfb070a355df8bbfc342b3234a4fb7375ad737ddbd98fd448f72429531e8fcc","sha256:052f83881ec2f25ffa5ce66e4a82f663f696e5f18499ce1d3e0b1b530232eca5"],"state_sha256":"aced239d29765e1929645094fd18f7929dc6de93095c97a78fbc77ff3ec120fe"}