{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E75DX5KVBREKNTN6ITPC3WXKVW","short_pith_number":"pith:E75DX5KV","schema_version":"1.0","canonical_sha256":"27fa3bf5550c48a6cdbe44de2ddaeaad8d3849eee0e24a710bf3c76846734790","source":{"kind":"arxiv","id":"2606.03078","version":1},"attestation_state":"computed","paper":{"title":"G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baijun Ji, Bohong Zhao, Longbo Sun, Rupu Wei, Xiangyu Duan, Yu Liu, Zixuan Zhou","submitted_at":"2026-06-02T03:09:15Z","abstract_excerpt":"Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and discourse-aware context selection. However, these approaches often lack an explicit mechanism for modeling structured discourse dependencies between distant paragraphs in a document. In this paper, we propose G^2C-MT (Graph-Guided Context for Machine Translation), which views DocMT context selection as a structured path discovery problem on a lightweight discourse graph, rather than retrieving unstructured context sets or relying on expensive 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":"2606.03078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T03:09:15Z","cross_cats_sorted":[],"title_canon_sha256":"787edada1ed66706e832b91e95263ca56b76886890e7d15a4be07057b4ad6dd0","abstract_canon_sha256":"d2b16d1d53f0d6313adcc7aa027513717411cfeef1ff30ecce4a2fe6b31c68f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:31.052123Z","signature_b64":"v1GvxtF6x7afHlxcNHz3O98w01URNAHYMEmF/9rr3rRV6LgRjQM8ezBlQBRkRiwVKmO6HtNYdtHiE6leEryfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27fa3bf5550c48a6cdbe44de2ddaeaad8d3849eee0e24a710bf3c76846734790","last_reissued_at":"2026-06-03T01:05:31.051696Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:31.051696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G^2C-MT: Graph-Guided Context Selection for Document-Level Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baijun Ji, Bohong Zhao, Longbo Sun, Rupu Wei, Xiangyu Duan, Yu Liu, Zixuan Zhou","submitted_at":"2026-06-02T03:09:15Z","abstract_excerpt":"Effective document-level machine translation (DocMT) requires capturing long-range discourse dependencies. Recent work has explored retrieval-based and discourse-aware context selection. However, these approaches often lack an explicit mechanism for modeling structured discourse dependencies between distant paragraphs in a document. In this paper, we propose G^2C-MT (Graph-Guided Context for Machine Translation), which views DocMT context selection as a structured path discovery problem on a lightweight discourse graph, rather than retrieving unstructured context sets or relying on expensive L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03078","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/2606.03078/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":"2606.03078","created_at":"2026-06-03T01:05:31.051756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03078v1","created_at":"2026-06-03T01:05:31.051756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03078","created_at":"2026-06-03T01:05:31.051756+00:00"},{"alias_kind":"pith_short_12","alias_value":"E75DX5KVBREK","created_at":"2026-06-03T01:05:31.051756+00:00"},{"alias_kind":"pith_short_16","alias_value":"E75DX5KVBREKNTN6","created_at":"2026-06-03T01:05:31.051756+00:00"},{"alias_kind":"pith_short_8","alias_value":"E75DX5KV","created_at":"2026-06-03T01:05:31.051756+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/E75DX5KVBREKNTN6ITPC3WXKVW","json":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW.json","graph_json":"https://pith.science/api/pith-number/E75DX5KVBREKNTN6ITPC3WXKVW/graph.json","events_json":"https://pith.science/api/pith-number/E75DX5KVBREKNTN6ITPC3WXKVW/events.json","paper":"https://pith.science/paper/E75DX5KV"},"agent_actions":{"view_html":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW","download_json":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW.json","view_paper":"https://pith.science/paper/E75DX5KV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03078&json=true","fetch_graph":"https://pith.science/api/pith-number/E75DX5KVBREKNTN6ITPC3WXKVW/graph.json","fetch_events":"https://pith.science/api/pith-number/E75DX5KVBREKNTN6ITPC3WXKVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW/action/storage_attestation","attest_author":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW/action/author_attestation","sign_citation":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW/action/citation_signature","submit_replication":"https://pith.science/pith/E75DX5KVBREKNTN6ITPC3WXKVW/action/replication_record"}},"created_at":"2026-06-03T01:05:31.051756+00:00","updated_at":"2026-06-03T01:05:31.051756+00:00"}