{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G2YIJWSDQGO5IUHW4LVGQ23XJQ","short_pith_number":"pith:G2YIJWSD","schema_version":"1.0","canonical_sha256":"36b084da43819dd450f6e2ea686b774c1246bef3c6a207b83eee4ba7ff14f425","source":{"kind":"arxiv","id":"2606.28796","version":1},"attestation_state":"computed","paper":{"title":"Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"A.R. Deshpande, Danish Chandargi, Manasi Waghe, Mohammad Aamir Rayyan, Raviraj Joshi","submitted_at":"2026-06-27T08:07:44Z","abstract_excerpt":"Government documents in India are predominantly issued in regional languages such as Marathi, creating substantial accessibility barriers for non-native readers, interstate administrative bodies, and policy analysts. Although recent advances in neural machine translation have improved sentence-level translation quality, existing systems largely neglect document structure, formatting integrity, and domain-specific terminology, thereby limiting their applicability to official documentation. This paper presents a structure-preserving Marathi-to-English government document translation framework ca"},"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":"2606.28796","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-27T08:07:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dd84ac04c8c19ed085a9129df8178cada8e9fded43972be00297145fd8e71f86","abstract_canon_sha256":"f7c85e387356d92826a366e436082eb2c448f201769424a73d3961307a68b45f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:52.347566Z","signature_b64":"6zvbc2YnvtP7pLlXj3jHUU8tsilnFi5A9vOZpXbqg/JSEE0SNBVKkaa6nttObkjxH0IdAFOWG2/3zz2PCMOiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36b084da43819dd450f6e2ea686b774c1246bef3c6a207b83eee4ba7ff14f425","last_reissued_at":"2026-06-30T01:16:52.347013Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:52.347013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Preserving Document Translation via Multi-Stage LLM Pipeline: A Case Study in Marathi","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"A.R. Deshpande, Danish Chandargi, Manasi Waghe, Mohammad Aamir Rayyan, Raviraj Joshi","submitted_at":"2026-06-27T08:07:44Z","abstract_excerpt":"Government documents in India are predominantly issued in regional languages such as Marathi, creating substantial accessibility barriers for non-native readers, interstate administrative bodies, and policy analysts. Although recent advances in neural machine translation have improved sentence-level translation quality, existing systems largely neglect document structure, formatting integrity, and domain-specific terminology, thereby limiting their applicability to official documentation. This paper presents a structure-preserving Marathi-to-English government document translation framework ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28796","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/2606.28796/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":"2606.28796","created_at":"2026-06-30T01:16:52.347108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28796v1","created_at":"2026-06-30T01:16:52.347108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28796","created_at":"2026-06-30T01:16:52.347108+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2YIJWSDQGO5","created_at":"2026-06-30T01:16:52.347108+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2YIJWSDQGO5IUHW","created_at":"2026-06-30T01:16:52.347108+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2YIJWSD","created_at":"2026-06-30T01:16:52.347108+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/G2YIJWSDQGO5IUHW4LVGQ23XJQ","json":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ.json","graph_json":"https://pith.science/api/pith-number/G2YIJWSDQGO5IUHW4LVGQ23XJQ/graph.json","events_json":"https://pith.science/api/pith-number/G2YIJWSDQGO5IUHW4LVGQ23XJQ/events.json","paper":"https://pith.science/paper/G2YIJWSD"},"agent_actions":{"view_html":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ","download_json":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ.json","view_paper":"https://pith.science/paper/G2YIJWSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28796&json=true","fetch_graph":"https://pith.science/api/pith-number/G2YIJWSDQGO5IUHW4LVGQ23XJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/G2YIJWSDQGO5IUHW4LVGQ23XJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ/action/storage_attestation","attest_author":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ/action/author_attestation","sign_citation":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ/action/citation_signature","submit_replication":"https://pith.science/pith/G2YIJWSDQGO5IUHW4LVGQ23XJQ/action/replication_record"}},"created_at":"2026-06-30T01:16:52.347108+00:00","updated_at":"2026-06-30T01:16:52.347108+00:00"}