{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:FRULHNU463ZN6IR6RGRDOLG56Z","short_pith_number":"pith:FRULHNU4","canonical_record":{"source":{"id":"1610.06510","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-20T17:32:32Z","cross_cats_sorted":[],"title_canon_sha256":"0d3f54c75ea39a0adfd2aaba448c04fc9ac04a1ef118f148f049917c6562a957","abstract_canon_sha256":"1f08b1a1ddf233dbf88f864cf4715ec70bc5df2961c2736b7b9297f21bc9a62f"},"schema_version":"1.0"},"canonical_sha256":"2c68b3b69cf6f2df223e89a2372cddf6767a8b5c4f06f389e69836de8c09d3f5","source":{"kind":"arxiv","id":"1610.06510","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.06510","created_at":"2026-05-18T00:39:52Z"},{"alias_kind":"arxiv_version","alias_value":"1610.06510v3","created_at":"2026-05-18T00:39:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.06510","created_at":"2026-05-18T00:39:52Z"},{"alias_kind":"pith_short_12","alias_value":"FRULHNU463ZN","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FRULHNU463ZN6IR6","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FRULHNU4","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:FRULHNU463ZN6IR6RGRDOLG56Z","target":"record","payload":{"canonical_record":{"source":{"id":"1610.06510","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-20T17:32:32Z","cross_cats_sorted":[],"title_canon_sha256":"0d3f54c75ea39a0adfd2aaba448c04fc9ac04a1ef118f148f049917c6562a957","abstract_canon_sha256":"1f08b1a1ddf233dbf88f864cf4715ec70bc5df2961c2736b7b9297f21bc9a62f"},"schema_version":"1.0"},"canonical_sha256":"2c68b3b69cf6f2df223e89a2372cddf6767a8b5c4f06f389e69836de8c09d3f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:52.850377Z","signature_b64":"wrO05397LzcFAEkt1nQTrfpOtQWU7PyZBNrUNUkUpyMNg5xeRR/ijvt2LGuqNNXrve9Tfozf6peUD8u0VTsjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c68b3b69cf6f2df223e89a2372cddf6767a8b5c4f06f389e69836de8c09d3f5","last_reissued_at":"2026-05-18T00:39:52.849907Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:52.849907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.06510","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LYeHcN9cUSUxSxHskNad34X8AGF6T8WT0klNMecrQ19uOJz8fQdMVP3uV6bhFA+RRDBOKnoeBfFgbM4RIJbfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T22:07:47.443340Z"},"content_sha256":"763adcf4dfa4f303f70346be47e55b5eaad1007cf80ac69359df8d1a873dee6f","schema_version":"1.0","event_id":"sha256:763adcf4dfa4f303f70346be47e55b5eaad1007cf80ac69359df8d1a873dee6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:FRULHNU463ZN6IR6RGRDOLG56Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning variable length units for SMT between related languages via Byte Pair Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Pushpak Bhattacharyya","submitted_at":"2016-10-20T17:32:32Z","abstract_excerpt":"We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11% increase in BLEU score. While orthographic syllables can"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.06510","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:39:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l6QkL5eWhXkSGmGT1uFm+XHlAqfIb0332lEJqslsVtuEWdrBXp8ep+6IaxCfpAU6qO/4gNfsTa3BWdhnBMV/Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T22:07:47.443697Z"},"content_sha256":"9b7c7f1fe5b517963d7caf73bf9185b6fbfea91a7146d2056c1eb00b1dba61ac","schema_version":"1.0","event_id":"sha256:9b7c7f1fe5b517963d7caf73bf9185b6fbfea91a7146d2056c1eb00b1dba61ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRULHNU463ZN6IR6RGRDOLG56Z/bundle.json","state_url":"https://pith.science/pith/FRULHNU463ZN6IR6RGRDOLG56Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRULHNU463ZN6IR6RGRDOLG56Z/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":"2026-07-24T22:07:47Z","links":{"resolver":"https://pith.science/pith/FRULHNU463ZN6IR6RGRDOLG56Z","bundle":"https://pith.science/pith/FRULHNU463ZN6IR6RGRDOLG56Z/bundle.json","state":"https://pith.science/pith/FRULHNU463ZN6IR6RGRDOLG56Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRULHNU463ZN6IR6RGRDOLG56Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:FRULHNU463ZN6IR6RGRDOLG56Z","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":"1f08b1a1ddf233dbf88f864cf4715ec70bc5df2961c2736b7b9297f21bc9a62f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-20T17:32:32Z","title_canon_sha256":"0d3f54c75ea39a0adfd2aaba448c04fc9ac04a1ef118f148f049917c6562a957"},"schema_version":"1.0","source":{"id":"1610.06510","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.06510","created_at":"2026-05-18T00:39:52Z"},{"alias_kind":"arxiv_version","alias_value":"1610.06510v3","created_at":"2026-05-18T00:39:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.06510","created_at":"2026-05-18T00:39:52Z"},{"alias_kind":"pith_short_12","alias_value":"FRULHNU463ZN","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FRULHNU463ZN6IR6","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FRULHNU4","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:9b7c7f1fe5b517963d7caf73bf9185b6fbfea91a7146d2056c1eb00b1dba61ac","target":"graph","created_at":"2026-05-18T00:39:52Z","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"},"paper":{"abstract_excerpt":"We explore the use of segments learnt using Byte Pair Encoding (referred to as BPE units) as basic units for statistical machine translation between related languages and compare it with orthographic syllables, which are currently the best performing basic units for this translation task. BPE identifies the most frequent character sequences as basic units, while orthographic syllables are linguistically motivated pseudo-syllables. We show that BPE units modestly outperform orthographic syllables as units of translation, showing up to 11% increase in BLEU score. While orthographic syllables can","authors_text":"Anoop Kunchukuttan, Pushpak Bhattacharyya","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-20T17:32:32Z","title":"Learning variable length units for SMT between related languages via Byte Pair Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.06510","kind":"arxiv","version":3},"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":"sha256:763adcf4dfa4f303f70346be47e55b5eaad1007cf80ac69359df8d1a873dee6f","target":"record","created_at":"2026-05-18T00:39:52Z","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":"1f08b1a1ddf233dbf88f864cf4715ec70bc5df2961c2736b7b9297f21bc9a62f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-10-20T17:32:32Z","title_canon_sha256":"0d3f54c75ea39a0adfd2aaba448c04fc9ac04a1ef118f148f049917c6562a957"},"schema_version":"1.0","source":{"id":"1610.06510","kind":"arxiv","version":3}},"canonical_sha256":"2c68b3b69cf6f2df223e89a2372cddf6767a8b5c4f06f389e69836de8c09d3f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c68b3b69cf6f2df223e89a2372cddf6767a8b5c4f06f389e69836de8c09d3f5","first_computed_at":"2026-05-18T00:39:52.849907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:52.849907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wrO05397LzcFAEkt1nQTrfpOtQWU7PyZBNrUNUkUpyMNg5xeRR/ijvt2LGuqNNXrve9Tfozf6peUD8u0VTsjDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:52.850377Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.06510","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:763adcf4dfa4f303f70346be47e55b5eaad1007cf80ac69359df8d1a873dee6f","sha256:9b7c7f1fe5b517963d7caf73bf9185b6fbfea91a7146d2056c1eb00b1dba61ac"],"state_sha256":"5ad7e9a17f2012b5db5de492480442ee56737d243bdb2e83dd7366f747e29eba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DWc0kcChn3ZdJSG5hEPmrJY7oYYQx80Tx8buAGSgdy0fpLSHehgRRRWqHo7BBrVERCFRJjAKYklbGFy30YXQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T22:07:47.446228Z","bundle_sha256":"0759e10e54361c41c9ebd75f181b7a0389d54f1280d27aed9ea72e120a88a00a"}}