{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Y6QODTK2B5E3RYP7IN4PFKPPUC","short_pith_number":"pith:Y6QODTK2","canonical_record":{"source":{"id":"2409.02712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:49:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18d34bc37e701ae58eedd814b606e984a021789e9103dc74b601aa863923f542","abstract_canon_sha256":"6e7ad5c77e56f03a4d640a36981f4c84ef09f0e349d9fd65e64f5a658d9ef926"},"schema_version":"1.0"},"canonical_sha256":"c7a0e1cd5a0f49b8e1ff4378f2a9efa09b0280b2c42bddf3c7823890f0443155","source":{"kind":"arxiv","id":"2409.02712","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02712","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02712v1","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02712","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"Y6QODTK2B5E3","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"Y6QODTK2B5E3RYP7","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"Y6QODTK2","created_at":"2026-07-05T09:03:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Y6QODTK2B5E3RYP7IN4PFKPPUC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02712","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:49:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18d34bc37e701ae58eedd814b606e984a021789e9103dc74b601aa863923f542","abstract_canon_sha256":"6e7ad5c77e56f03a4d640a36981f4c84ef09f0e349d9fd65e64f5a658d9ef926"},"schema_version":"1.0"},"canonical_sha256":"c7a0e1cd5a0f49b8e1ff4378f2a9efa09b0280b2c42bddf3c7823890f0443155","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:09.110667Z","signature_b64":"Dm7HmzG4LiU8EtKQ8tghs9mCMcXZla6Ve4lQVfWzKtxgRqsw/E0mR0ufi/G5EacdgGwGPxK0fUuYkgc8hpWmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a0e1cd5a0f49b8e1ff4378f2a9efa09b0280b2c42bddf3c7823890f0443155","last_reissued_at":"2026-07-05T09:03:09.110229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:09.110229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02712","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":"2026-07-05T09:03:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k9wzNdcWg3AzGbxf7df0blur6PHbIUM0zdG4dye37tVpdeUhUt2E9ggtxuj+T2y3656A225Fl8Mf6lR06L1jCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:22:32.612477Z"},"content_sha256":"d9e3f1922c87c0ca626ae9a3b6e3e6d46ab8c8dfaa6a571907fe796dddadc8a7","schema_version":"1.0","event_id":"sha256:d9e3f1922c87c0ca626ae9a3b6e3e6d46ab8c8dfaa6a571907fe796dddadc8a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Y6QODTK2B5E3RYP7IN4PFKPPUC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Nidhi Kowtal, Raviraj Joshi, Tejas Deshpande","submitted_at":"2024-09-04T13:49:45Z","abstract_excerpt":"Machine translation in low-resource language pairs faces significant challenges due to the scarcity of parallel corpora and linguistic resources. This study focuses on the case of English-Marathi language pairs, where existing datasets are notably noisy, impeding the performance of machine translation models. To mitigate the impact of data quality issues, we propose a data filtering approach based on cross-lingual sentence representations. Our methodology leverages a multilingual SBERT model to filter out problematic translations in the training data. Specifically, we employ an IndicSBERT simi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02712","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/2409.02712/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":"2026-07-05T09:03:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jiggZbC2C2IQUM9QQFOyCyjDXm2qt7VxV2GQvT/UACgB/lOIxe+tZjuRZG8tKYD7MEuUHFFhj+2btroEGVeuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:22:32.612855Z"},"content_sha256":"f87c3055bfb2fe3c68ad98f1020710d6465c411d386bc759424fd2bfee038463","schema_version":"1.0","event_id":"sha256:f87c3055bfb2fe3c68ad98f1020710d6465c411d386bc759424fd2bfee038463"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC/bundle.json","state_url":"https://pith.science/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC/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":"2026-07-07T09:22:32Z","links":{"resolver":"https://pith.science/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC","bundle":"https://pith.science/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC/bundle.json","state":"https://pith.science/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y6QODTK2B5E3RYP7IN4PFKPPUC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y6QODTK2B5E3RYP7IN4PFKPPUC","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":"6e7ad5c77e56f03a4d640a36981f4c84ef09f0e349d9fd65e64f5a658d9ef926","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:49:45Z","title_canon_sha256":"18d34bc37e701ae58eedd814b606e984a021789e9103dc74b601aa863923f542"},"schema_version":"1.0","source":{"id":"2409.02712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02712","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02712v1","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02712","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"Y6QODTK2B5E3","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"Y6QODTK2B5E3RYP7","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"Y6QODTK2","created_at":"2026-07-05T09:03:09Z"}],"graph_snapshots":[{"event_id":"sha256:f87c3055bfb2fe3c68ad98f1020710d6465c411d386bc759424fd2bfee038463","target":"graph","created_at":"2026-07-05T09:03:09Z","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/2409.02712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine translation in low-resource language pairs faces significant challenges due to the scarcity of parallel corpora and linguistic resources. This study focuses on the case of English-Marathi language pairs, where existing datasets are notably noisy, impeding the performance of machine translation models. To mitigate the impact of data quality issues, we propose a data filtering approach based on cross-lingual sentence representations. Our methodology leverages a multilingual SBERT model to filter out problematic translations in the training data. Specifically, we employ an IndicSBERT simi","authors_text":"Nidhi Kowtal, Raviraj Joshi, Tejas Deshpande","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:49:45Z","title":"A Data Selection Approach for Enhancing Low Resource Machine Translation Using Cross-Lingual Sentence Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02712","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:d9e3f1922c87c0ca626ae9a3b6e3e6d46ab8c8dfaa6a571907fe796dddadc8a7","target":"record","created_at":"2026-07-05T09:03:09Z","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":"6e7ad5c77e56f03a4d640a36981f4c84ef09f0e349d9fd65e64f5a658d9ef926","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:49:45Z","title_canon_sha256":"18d34bc37e701ae58eedd814b606e984a021789e9103dc74b601aa863923f542"},"schema_version":"1.0","source":{"id":"2409.02712","kind":"arxiv","version":1}},"canonical_sha256":"c7a0e1cd5a0f49b8e1ff4378f2a9efa09b0280b2c42bddf3c7823890f0443155","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7a0e1cd5a0f49b8e1ff4378f2a9efa09b0280b2c42bddf3c7823890f0443155","first_computed_at":"2026-07-05T09:03:09.110229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:09.110229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dm7HmzG4LiU8EtKQ8tghs9mCMcXZla6Ve4lQVfWzKtxgRqsw/E0mR0ufi/G5EacdgGwGPxK0fUuYkgc8hpWmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:09.110667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9e3f1922c87c0ca626ae9a3b6e3e6d46ab8c8dfaa6a571907fe796dddadc8a7","sha256:f87c3055bfb2fe3c68ad98f1020710d6465c411d386bc759424fd2bfee038463"],"state_sha256":"789277425328300ea5c68b48755a1c39e5eb6415e2268766eb953c76da870040"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4WXUPnisgY81kzQbbfssPhROmwyEg4zo3+Gf8Ih8i3sHaMSla7jbFx0THZj7Td/7u7mgO57TYq+1qelZ/ByTBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:22:32.614787Z","bundle_sha256":"e0fd6d6c8a672afc7cde9d39d852398ec852184c9e50f4f4ece3e321bf34956b"}}