{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CF4CERKSBRSVF5PF6V3GS7KDSW","short_pith_number":"pith:CF4CERKS","canonical_record":{"source":{"id":"2412.16877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T06:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"a23e8aeca0e71f64dbbd62328c0dd075217470ee3ace9dbfca7a79c4d595de29","abstract_canon_sha256":"12c99001a6cd153e6acbf282872149e29f0cb897e6a656b41812a417e8239f50"},"schema_version":"1.0"},"canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","source":{"kind":"arxiv","id":"2412.16877","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16877","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16877v1","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16877","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"CF4CERKSBRSV","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"CF4CERKSBRSVF5PF","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"CF4CERKS","created_at":"2026-07-05T09:53:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CF4CERKSBRSVF5PF6V3GS7KDSW","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T06:12:46Z","cross_cats_sorted":[],"title_canon_sha256":"a23e8aeca0e71f64dbbd62328c0dd075217470ee3ace9dbfca7a79c4d595de29","abstract_canon_sha256":"12c99001a6cd153e6acbf282872149e29f0cb897e6a656b41812a417e8239f50"},"schema_version":"1.0"},"canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:14.050786Z","signature_b64":"9lMtco3YHFYqkRNrq88vBXOfvIEeggZyzU4/4mR+K6+Da1lFNCJL4JIWv1ZEMQn5xGtinChPr0oyQBfrE2ZNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","last_reissued_at":"2026-07-05T09:53:14.050355Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:14.050355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16877","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":"2026-07-05T09:53:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+++kUECOS4pRF+0IsWmrdrBI/fW1lo18fiOZsZ6vpdNK81PmxC92pSQeMQKUBhKuUUGUmlU8safUxAxR+VECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:41:16.279924Z"},"content_sha256":"88912e439f698b52584a7d54ccf738446c8008713d694b6e227bb3a88812a0e8","schema_version":"1.0","event_id":"sha256:88912e439f698b52584a7d54ccf738446c8008713d694b6e227bb3a88812a0e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CF4CERKSBRSVF5PF6V3GS7KDSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reconsidering SMT Over NMT for Closely Related Languages: A Case Study of Persian-Hindi Pair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pushpak Bhattacharyya, Waisullah Yousofi","submitted_at":"2024-12-22T06:12:46Z","abstract_excerpt":"This paper demonstrates that Phrase-Based Statistical Machine Translation (PBSMT) can outperform Transformer-based Neural Machine Translation (NMT) in moderate-resource scenarios, specifically for structurally similar languages, like the Persian-Hindi pair. Despite the Transformer architecture's typical preference for large parallel corpora, our results show that PBSMT achieves a BLEU score of 66.32, significantly exceeding the Transformer-NMT score of 53.7 on the same dataset. Additionally, we explore variations of the SMT architecture, including training on Romanized text and modifying the w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16877","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/2412.16877/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":"2026-07-05T09:53:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NiQR6Kj714muhTpmsX3g14sYrsgL8agXQam6dioNUcWuPdeb/P2UIT8XrkVMxt5fbb+OcG2HPYe0im21HuSmAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:41:16.280444Z"},"content_sha256":"b49788e8b0d79fdb137e216513a3a8af54776b2dfc64009de1bd30526f281236","schema_version":"1.0","event_id":"sha256:b49788e8b0d79fdb137e216513a3a8af54776b2dfc64009de1bd30526f281236"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/bundle.json","state_url":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/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":"2026-08-15T18:41:16Z","links":{"resolver":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW","bundle":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/bundle.json","state":"https://pith.science/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CF4CERKSBRSVF5PF6V3GS7KDSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CF4CERKSBRSVF5PF6V3GS7KDSW","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":"12c99001a6cd153e6acbf282872149e29f0cb897e6a656b41812a417e8239f50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T06:12:46Z","title_canon_sha256":"a23e8aeca0e71f64dbbd62328c0dd075217470ee3ace9dbfca7a79c4d595de29"},"schema_version":"1.0","source":{"id":"2412.16877","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16877","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16877v1","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16877","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"CF4CERKSBRSV","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"CF4CERKSBRSVF5PF","created_at":"2026-07-05T09:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"CF4CERKS","created_at":"2026-07-05T09:53:14Z"}],"graph_snapshots":[{"event_id":"sha256:b49788e8b0d79fdb137e216513a3a8af54776b2dfc64009de1bd30526f281236","target":"graph","created_at":"2026-07-05T09:53:14Z","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/2412.16877/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper demonstrates that Phrase-Based Statistical Machine Translation (PBSMT) can outperform Transformer-based Neural Machine Translation (NMT) in moderate-resource scenarios, specifically for structurally similar languages, like the Persian-Hindi pair. Despite the Transformer architecture's typical preference for large parallel corpora, our results show that PBSMT achieves a BLEU score of 66.32, significantly exceeding the Transformer-NMT score of 53.7 on the same dataset. Additionally, we explore variations of the SMT architecture, including training on Romanized text and modifying the w","authors_text":"Pushpak Bhattacharyya, Waisullah Yousofi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T06:12:46Z","title":"Reconsidering SMT Over NMT for Closely Related Languages: A Case Study of Persian-Hindi Pair"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16877","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":"sha256:88912e439f698b52584a7d54ccf738446c8008713d694b6e227bb3a88812a0e8","target":"record","created_at":"2026-07-05T09:53:14Z","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":"12c99001a6cd153e6acbf282872149e29f0cb897e6a656b41812a417e8239f50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T06:12:46Z","title_canon_sha256":"a23e8aeca0e71f64dbbd62328c0dd075217470ee3ace9dbfca7a79c4d595de29"},"schema_version":"1.0","source":{"id":"2412.16877","kind":"arxiv","version":1}},"canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11782245520c6552f5e5f576697d43959be7c1039c1edd0d8ca9689945ed115d","first_computed_at":"2026-07-05T09:53:14.050355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:14.050355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9lMtco3YHFYqkRNrq88vBXOfvIEeggZyzU4/4mR+K6+Da1lFNCJL4JIWv1ZEMQn5xGtinChPr0oyQBfrE2ZNAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:14.050786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16877","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88912e439f698b52584a7d54ccf738446c8008713d694b6e227bb3a88812a0e8","sha256:b49788e8b0d79fdb137e216513a3a8af54776b2dfc64009de1bd30526f281236"],"state_sha256":"3fd8c1c26b09653d9fd5832e9211523dc8277c05dd43bef66416a115b98e5892"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XeCFSeIFiOvQIHWbB1Zs3ZVe4TrQJhEZgG1yfYOyi7lP155sCpi43rFGSnGyVG4aq+9VZXgEZQTZZIaD7FqjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:41:16.285975Z","bundle_sha256":"4074311e9ae84138c9c84bfcfd7d200c46489baafeb775de45bcdeb4053f984c"}}