{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:GBRDSX47XHRS5LRL34MH3GWMXV","short_pith_number":"pith:GBRDSX47","canonical_record":{"source":{"id":"1609.01188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-05T14:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"f12b168ba4799dc4d88ba3b4dd631d7842cf611e638d6e0653ed9985fadc29a0","abstract_canon_sha256":"d49f71c4b2407cdb3d8975997b949e7befd35a82fe56da2a13b1111254009258"},"schema_version":"1.0"},"canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","source":{"kind":"arxiv","id":"1609.01188","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.01188","created_at":"2026-05-18T01:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"1609.01188v1","created_at":"2026-05-18T01:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01188","created_at":"2026-05-18T01:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"GBRDSX47XHRS","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"GBRDSX47XHRS5LRL","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"GBRDSX47","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:GBRDSX47XHRS5LRL34MH3GWMXV","target":"record","payload":{"canonical_record":{"source":{"id":"1609.01188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-05T14:55:31Z","cross_cats_sorted":[],"title_canon_sha256":"f12b168ba4799dc4d88ba3b4dd631d7842cf611e638d6e0653ed9985fadc29a0","abstract_canon_sha256":"d49f71c4b2407cdb3d8975997b949e7befd35a82fe56da2a13b1111254009258"},"schema_version":"1.0"},"canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:06:18.758689Z","signature_b64":"TIbRB7x6R3nz1+QU5Ld8WcXkQrnGzT7Q14DUyvWHXgcY7yfOGUe3RpUKEq6zf32yiT4aYDFvhbwskjcVFG9vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","last_reissued_at":"2026-05-18T01:06:18.758191Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:06:18.758191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.01188","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":"2026-05-18T01:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cOtAHTWhGtrqYbCvPeJChR0N49RXplUMCs6wA4iFdqTC3IDrVPRtBJFMdfcs6E/8dwjHKQjISpH5Z23ii7DCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:17:54.364698Z"},"content_sha256":"d96d591a704ed924bb063e8aef49fc0d9f5e6ade24ddc7bc330be5c54eec3914","schema_version":"1.0","event_id":"sha256:d96d591a704ed924bb063e8aef49fc0d9f5e6ade24ddc7bc330be5c54eec3914"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:GBRDSX47XHRS5LRL34MH3GWMXV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahad Al-Obaidli, Preslav Nakov, Stephen Cox","submitted_at":"2016-09-05T14:55:31Z","abstract_excerpt":"We describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01188","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":""},"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":"2026-05-18T01:06:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNV+sZpJjuXToxMsFZD5/ur5ftr7TEgAJ7sgPf9KBypwwWnovOriTCm3PmwV/jNjgCa1nOz4FE6N3oMo38R+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T10:17:54.365407Z"},"content_sha256":"5269f5a2b5bf2804e23a7f910382631b9bed52e586593c9a8256f247d2e19781","schema_version":"1.0","event_id":"sha256:5269f5a2b5bf2804e23a7f910382631b9bed52e586593c9a8256f247d2e19781"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/bundle.json","state_url":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBRDSX47XHRS5LRL34MH3GWMXV/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":"2026-05-27T10:17:54Z","links":{"resolver":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV","bundle":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/bundle.json","state":"https://pith.science/pith/GBRDSX47XHRS5LRL34MH3GWMXV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBRDSX47XHRS5LRL34MH3GWMXV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:GBRDSX47XHRS5LRL34MH3GWMXV","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":"d49f71c4b2407cdb3d8975997b949e7befd35a82fe56da2a13b1111254009258","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-05T14:55:31Z","title_canon_sha256":"f12b168ba4799dc4d88ba3b4dd631d7842cf611e638d6e0653ed9985fadc29a0"},"schema_version":"1.0","source":{"id":"1609.01188","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.01188","created_at":"2026-05-18T01:06:18Z"},{"alias_kind":"arxiv_version","alias_value":"1609.01188v1","created_at":"2026-05-18T01:06:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01188","created_at":"2026-05-18T01:06:18Z"},{"alias_kind":"pith_short_12","alias_value":"GBRDSX47XHRS","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"GBRDSX47XHRS5LRL","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"GBRDSX47","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:5269f5a2b5bf2804e23a7f910382631b9bed52e586593c9a8256f247d2e19781","target":"graph","created_at":"2026-05-18T01:06:18Z","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 describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this ","authors_text":"Fahad Al-Obaidli, Preslav Nakov, Stephen Cox","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-05T14:55:31Z","title":"Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01188","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:d96d591a704ed924bb063e8aef49fc0d9f5e6ade24ddc7bc330be5c54eec3914","target":"record","created_at":"2026-05-18T01:06:18Z","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":"d49f71c4b2407cdb3d8975997b949e7befd35a82fe56da2a13b1111254009258","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-05T14:55:31Z","title_canon_sha256":"f12b168ba4799dc4d88ba3b4dd631d7842cf611e638d6e0653ed9985fadc29a0"},"schema_version":"1.0","source":{"id":"1609.01188","kind":"arxiv","version":1}},"canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3062395f9fb9e32eae2bdf187d9accbd74b6b88703056f1111993905bcf4a31e","first_computed_at":"2026-05-18T01:06:18.758191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:06:18.758191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TIbRB7x6R3nz1+QU5Ld8WcXkQrnGzT7Q14DUyvWHXgcY7yfOGUe3RpUKEq6zf32yiT4aYDFvhbwskjcVFG9vDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:06:18.758689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.01188","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d96d591a704ed924bb063e8aef49fc0d9f5e6ade24ddc7bc330be5c54eec3914","sha256:5269f5a2b5bf2804e23a7f910382631b9bed52e586593c9a8256f247d2e19781"],"state_sha256":"1cc7d47831036a257f0b8e68682154f727dcacca334015317be57e4880c4a642"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fC/SBc/+3U2JGQQY5gHO8Fq16+SPV5uIysgMrh0mxxmnLBJ+T8N//HoDLy0fRcLUooYfsWu0U2uR5YPR3PJ6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T10:17:54.369259Z","bundle_sha256":"05d89d9d09dd4bb54808c2f8c65510a640f140e754503707f0856f60cf6c0aaa"}}