{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZBDYEJD6CGYDZ32H63OBZ3UJST","short_pith_number":"pith:ZBDYEJD6","canonical_record":{"source":{"id":"2003.08925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T17:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"872fbc395a7b1e0117ce7b3333ea178493fdfa6d5a31d1b0799a6fb1b0cb8296","abstract_canon_sha256":"aba20070b09ec94e71e35fa9a0f8f02c421cd4430871031b2469671b07271a5b"},"schema_version":"1.0"},"canonical_sha256":"c84782247e11b03cef47f6dc1cee8994d09ec8ebb1b20766882decf30f14e139","source":{"kind":"arxiv","id":"2003.08925","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08925","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08925v1","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08925","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZBDYEJD6CGYD","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"ZBDYEJD6CGYDZ32H","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"ZBDYEJD6","created_at":"2026-07-05T00:49:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZBDYEJD6CGYDZ32H63OBZ3UJST","target":"record","payload":{"canonical_record":{"source":{"id":"2003.08925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T17:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"872fbc395a7b1e0117ce7b3333ea178493fdfa6d5a31d1b0799a6fb1b0cb8296","abstract_canon_sha256":"aba20070b09ec94e71e35fa9a0f8f02c421cd4430871031b2469671b07271a5b"},"schema_version":"1.0"},"canonical_sha256":"c84782247e11b03cef47f6dc1cee8994d09ec8ebb1b20766882decf30f14e139","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:21.781587Z","signature_b64":"rlDJ059L+KFMcSiDF4dhoYE0KlRrCP8+ShjsRjkI+WMN4A8a2xdQlX9Ii40E+IU4lZhJ+olAuKBgUjEliQWYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c84782247e11b03cef47f6dc1cee8994d09ec8ebb1b20766882decf30f14e139","last_reissued_at":"2026-07-05T00:49:21.781112Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:21.781112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.08925","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":"2026-07-05T00:49:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKSuuCNVVMENeZwOgUWrwolOevWrLqnEXA+f6at04kwCUHVnB4+2qFEPnXtwfn7bTcCQaiss/Ndx9YUcFcrACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:22:03.174764Z"},"content_sha256":"ceaa0f1f4fa0b2dbee1145f2b6caa11e1d821d67aac153dfe227f8f412d44b05","schema_version":"1.0","event_id":"sha256:ceaa0f1f4fa0b2dbee1145f2b6caa11e1d821d67aac153dfe227f8f412d44b05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZBDYEJD6CGYDZ32H63OBZ3UJST","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Pushpak Bhattacharyya","submitted_at":"2020-03-19T17:43:28Z","abstract_excerpt":"In this work, we present an extensive study of statistical machine translation involving languages of the Indian subcontinent. These languages are related by genetic and contact relationships. We describe the similarities between Indic languages arising from these relationships. We explore how lexical and orthographic similarity among these languages can be utilized to improve translation quality between Indic languages when limited parallel corpora is available. We also explore how the structural correspondence between Indic languages can be utilized to re-use linguistic resources for English"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08925","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/2003.08925/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":"2026-07-05T00:49:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RIgp+O1GI32qhfPtTZRlCkIn4/7/W557RRHj6CEMMnHL/F4EQ86Jr1idrmg0g6aHNDL4mpdFjsgMu2cnzmx6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:22:03.175274Z"},"content_sha256":"4874d08c8a3d44d7aa1ab4d0574fda621fed2d50110ba3433ab1ae5d36736c20","schema_version":"1.0","event_id":"sha256:4874d08c8a3d44d7aa1ab4d0574fda621fed2d50110ba3433ab1ae5d36736c20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST/bundle.json","state_url":"https://pith.science/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST/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":"2026-08-04T10:22:03Z","links":{"resolver":"https://pith.science/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST","bundle":"https://pith.science/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST/bundle.json","state":"https://pith.science/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBDYEJD6CGYDZ32H63OBZ3UJST/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZBDYEJD6CGYDZ32H63OBZ3UJST","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":"aba20070b09ec94e71e35fa9a0f8f02c421cd4430871031b2469671b07271a5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T17:43:28Z","title_canon_sha256":"872fbc395a7b1e0117ce7b3333ea178493fdfa6d5a31d1b0799a6fb1b0cb8296"},"schema_version":"1.0","source":{"id":"2003.08925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.08925","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"arxiv_version","alias_value":"2003.08925v1","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.08925","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"pith_short_12","alias_value":"ZBDYEJD6CGYD","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"pith_short_16","alias_value":"ZBDYEJD6CGYDZ32H","created_at":"2026-07-05T00:49:21Z"},{"alias_kind":"pith_short_8","alias_value":"ZBDYEJD6","created_at":"2026-07-05T00:49:21Z"}],"graph_snapshots":[{"event_id":"sha256:4874d08c8a3d44d7aa1ab4d0574fda621fed2d50110ba3433ab1ae5d36736c20","target":"graph","created_at":"2026-07-05T00:49:21Z","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/2003.08925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present an extensive study of statistical machine translation involving languages of the Indian subcontinent. These languages are related by genetic and contact relationships. We describe the similarities between Indic languages arising from these relationships. We explore how lexical and orthographic similarity among these languages can be utilized to improve translation quality between Indic languages when limited parallel corpora is available. We also explore how the structural correspondence between Indic languages can be utilized to re-use linguistic resources for English","authors_text":"Anoop Kunchukuttan, Pushpak Bhattacharyya","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T17:43:28Z","title":"Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.08925","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:ceaa0f1f4fa0b2dbee1145f2b6caa11e1d821d67aac153dfe227f8f412d44b05","target":"record","created_at":"2026-07-05T00:49:21Z","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":"aba20070b09ec94e71e35fa9a0f8f02c421cd4430871031b2469671b07271a5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-19T17:43:28Z","title_canon_sha256":"872fbc395a7b1e0117ce7b3333ea178493fdfa6d5a31d1b0799a6fb1b0cb8296"},"schema_version":"1.0","source":{"id":"2003.08925","kind":"arxiv","version":1}},"canonical_sha256":"c84782247e11b03cef47f6dc1cee8994d09ec8ebb1b20766882decf30f14e139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c84782247e11b03cef47f6dc1cee8994d09ec8ebb1b20766882decf30f14e139","first_computed_at":"2026-07-05T00:49:21.781112Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:49:21.781112Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rlDJ059L+KFMcSiDF4dhoYE0KlRrCP8+ShjsRjkI+WMN4A8a2xdQlX9Ii40E+IU4lZhJ+olAuKBgUjEliQWYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:49:21.781587Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.08925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ceaa0f1f4fa0b2dbee1145f2b6caa11e1d821d67aac153dfe227f8f412d44b05","sha256:4874d08c8a3d44d7aa1ab4d0574fda621fed2d50110ba3433ab1ae5d36736c20"],"state_sha256":"5cfacde8e6e9ffe9db1e002b58227ed8f5c95cd926f711ee09670c5ec8d60807"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3GTeRvbh+L4himTTA63Jlxoqe9cpCkLs0PJ/t/o5QCyqOs0rL72Y+6VkGHs2U7Kd/vLrg/nkTfljiDEaWDJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:22:03.180179Z","bundle_sha256":"d16af3a980489c38b9c0df04797ad224d3622572a712f36ca8450a5cfd9dfdeb"}}