{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JPNHJ4UPVSEEMNHPU64FD26SB2","short_pith_number":"pith:JPNHJ4UP","schema_version":"1.0","canonical_sha256":"4bda74f28fac884634efa7b851ebd20eac117ff2b291ded858879e7e5a9f261e","source":{"kind":"arxiv","id":"2607.18618","version":1},"attestation_state":"computed","paper":{"title":"LatentMT: Machine Translation with Latent Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Muhammad Abdul-Mageed, Samar M. Magdy, Wei-Rui Chen, Wenhui Zhu, Zhipeng Wang","submitted_at":"2026-07-21T01:38:23Z","abstract_excerpt":"Latent-reasoning looped language models (LoopLMs) offer a different scaling path for machine translation (MT): instead of increasing parameter count or emitting explicit chain-of-thought tokens, they spend additional recurrent computation inside hidden states. We introduce LatentMT, the first systematic study of latent-reasoning LoopLMs for machine translation. LatentMT adapts a small 2.6B-parameter backbone model with lightweight training. Across 32 translation directions spanning high-, mid-, and low-resource languages, LatentMT achieves performance comparable to models three to five times l"},"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":"2607.18618","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T01:38:23Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c24e113092d291c1a83e0e54123b66cd6d07c5ec730400a0617938fbfb1ad7e7","abstract_canon_sha256":"53279a15db461acd95357a2cfd8da074dbe37eb4d1485cc4e64c6f43854aa44b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T00:22:57.037349Z","signature_b64":"iBQhXqcCYVjiamSak+R1+E+fnVosxM5ZI0XUlKzj4gHxIVjIoWdzbUZ3ahiLYnx3Cn67Pg1w6zc4LmOy9DiVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bda74f28fac884634efa7b851ebd20eac117ff2b291ded858879e7e5a9f261e","last_reissued_at":"2026-07-22T00:22:57.036535Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T00:22:57.036535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LatentMT: Machine Translation with Latent Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chiyu Zhang, Muhammad Abdul-Mageed, Samar M. Magdy, Wei-Rui Chen, Wenhui Zhu, Zhipeng Wang","submitted_at":"2026-07-21T01:38:23Z","abstract_excerpt":"Latent-reasoning looped language models (LoopLMs) offer a different scaling path for machine translation (MT): instead of increasing parameter count or emitting explicit chain-of-thought tokens, they spend additional recurrent computation inside hidden states. We introduce LatentMT, the first systematic study of latent-reasoning LoopLMs for machine translation. LatentMT adapts a small 2.6B-parameter backbone model with lightweight training. Across 32 translation directions spanning high-, mid-, and low-resource languages, LatentMT achieves performance comparable to models three to five times l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18618","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/2607.18618/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.18618","created_at":"2026-07-22T00:22:57.036963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.18618v1","created_at":"2026-07-22T00:22:57.036963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18618","created_at":"2026-07-22T00:22:57.036963+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPNHJ4UPVSEE","created_at":"2026-07-22T00:22:57.036963+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPNHJ4UPVSEEMNHP","created_at":"2026-07-22T00:22:57.036963+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPNHJ4UP","created_at":"2026-07-22T00:22:57.036963+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/JPNHJ4UPVSEEMNHPU64FD26SB2","json":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2.json","graph_json":"https://pith.science/api/pith-number/JPNHJ4UPVSEEMNHPU64FD26SB2/graph.json","events_json":"https://pith.science/api/pith-number/JPNHJ4UPVSEEMNHPU64FD26SB2/events.json","paper":"https://pith.science/paper/JPNHJ4UP"},"agent_actions":{"view_html":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2","download_json":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2.json","view_paper":"https://pith.science/paper/JPNHJ4UP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.18618&json=true","fetch_graph":"https://pith.science/api/pith-number/JPNHJ4UPVSEEMNHPU64FD26SB2/graph.json","fetch_events":"https://pith.science/api/pith-number/JPNHJ4UPVSEEMNHPU64FD26SB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2/action/storage_attestation","attest_author":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2/action/author_attestation","sign_citation":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2/action/citation_signature","submit_replication":"https://pith.science/pith/JPNHJ4UPVSEEMNHPU64FD26SB2/action/replication_record"}},"created_at":"2026-07-22T00:22:57.036963+00:00","updated_at":"2026-07-22T00:22:57.036963+00:00"}