{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:C2KTUKG5RTSH5XJBCVYCBYY3QH","short_pith_number":"pith:C2KTUKG5","canonical_record":{"source":{"id":"1502.03752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T17:49:45Z","cross_cats_sorted":[],"title_canon_sha256":"886978630508d58b32f11fa804cdff9e7a88d8c5aa91578cc7dbc427256bb585","abstract_canon_sha256":"f613e859d927f91666ffcbf1c23aee765a9e0aeef90ab31f9dec6324b5642a46"},"schema_version":"1.0"},"canonical_sha256":"16953a28dd8ce47edd21157020e31b81f374235f468c09a28fbff6e28794e5ce","source":{"kind":"arxiv","id":"1502.03752","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.03752","created_at":"2026-05-18T02:27:16Z"},{"alias_kind":"arxiv_version","alias_value":"1502.03752v1","created_at":"2026-05-18T02:27:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03752","created_at":"2026-05-18T02:27:16Z"},{"alias_kind":"pith_short_12","alias_value":"C2KTUKG5RTSH","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"C2KTUKG5RTSH5XJB","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"C2KTUKG5","created_at":"2026-05-18T12:29:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:C2KTUKG5RTSH5XJBCVYCBYY3QH","target":"record","payload":{"canonical_record":{"source":{"id":"1502.03752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T17:49:45Z","cross_cats_sorted":[],"title_canon_sha256":"886978630508d58b32f11fa804cdff9e7a88d8c5aa91578cc7dbc427256bb585","abstract_canon_sha256":"f613e859d927f91666ffcbf1c23aee765a9e0aeef90ab31f9dec6324b5642a46"},"schema_version":"1.0"},"canonical_sha256":"16953a28dd8ce47edd21157020e31b81f374235f468c09a28fbff6e28794e5ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:27:16.807621Z","signature_b64":"b9KO8J9YZZgMxmHqqAVgsHYlNOgjHx7bMv4P3XfHlVqmoHfj1ZMMeB4C/NykhoKpz6IfIGn2IdkIDcygQm0DCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16953a28dd8ce47edd21157020e31b81f374235f468c09a28fbff6e28794e5ce","last_reissued_at":"2026-05-18T02:27:16.806910Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:27:16.806910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.03752","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":"2026-05-18T02:27:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fn0jZgxYPyYI6q3Mr9FqNunp3zbLdAwRR7HMx6/ZF0iONd19johRWNmaPlXx+LRi0H6Bzo7h9ZsEJYk6KiH3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T09:59:03.270856Z"},"content_sha256":"647cb6465fa9aa747075b887fe6a788c83a6f7b65685fd769d238da9cf53676e","schema_version":"1.0","event_id":"sha256:647cb6465fa9aa747075b887fe6a788c83a6f7b65685fd769d238da9cf53676e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:C2KTUKG5RTSH5XJBCVYCBYY3QH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A new hybrid metric for verifying parallel corpora of Arabic-English","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Saad Alkahtani, Wei Liu, William J. Teahan","submitted_at":"2015-02-12T17:49:45Z","abstract_excerpt":"This paper discusses a new metric that has been applied to verify the quality in translation between sentence pairs in parallel corpora of Arabic-English. This metric combines two techniques, one based on sentence length and the other based on compression code length. Experiments on sample test parallel Arabic-English corpora indicate the combination of these two techniques improves accuracy of the identification of satisfactory and unsatisfactory sentence pairs compared to sentence length and compression code length alone. The new method proposed in this research is effective at filtering noi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03752","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":"2026-05-18T02:27:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WUO3gQORpqJeoTXk021/3mGNHNJQ9Uvd+eIi4+tAWM+J+R4lwUB5Rlv4/Rh+7+T5hRQA1GBEt0+zs0stNbvWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T09:59:03.271202Z"},"content_sha256":"a0ad87f550f45be100e5e1a6d9d32b4082a53d4d1250ad87bdd8a1e7a335e732","schema_version":"1.0","event_id":"sha256:a0ad87f550f45be100e5e1a6d9d32b4082a53d4d1250ad87bdd8a1e7a335e732"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH/bundle.json","state_url":"https://pith.science/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH/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":"2026-07-03T09:59:03Z","links":{"resolver":"https://pith.science/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH","bundle":"https://pith.science/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH/bundle.json","state":"https://pith.science/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2KTUKG5RTSH5XJBCVYCBYY3QH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:C2KTUKG5RTSH5XJBCVYCBYY3QH","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":"f613e859d927f91666ffcbf1c23aee765a9e0aeef90ab31f9dec6324b5642a46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T17:49:45Z","title_canon_sha256":"886978630508d58b32f11fa804cdff9e7a88d8c5aa91578cc7dbc427256bb585"},"schema_version":"1.0","source":{"id":"1502.03752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.03752","created_at":"2026-05-18T02:27:16Z"},{"alias_kind":"arxiv_version","alias_value":"1502.03752v1","created_at":"2026-05-18T02:27:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.03752","created_at":"2026-05-18T02:27:16Z"},{"alias_kind":"pith_short_12","alias_value":"C2KTUKG5RTSH","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_16","alias_value":"C2KTUKG5RTSH5XJB","created_at":"2026-05-18T12:29:14Z"},{"alias_kind":"pith_short_8","alias_value":"C2KTUKG5","created_at":"2026-05-18T12:29:14Z"}],"graph_snapshots":[{"event_id":"sha256:a0ad87f550f45be100e5e1a6d9d32b4082a53d4d1250ad87bdd8a1e7a335e732","target":"graph","created_at":"2026-05-18T02:27:16Z","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":"This paper discusses a new metric that has been applied to verify the quality in translation between sentence pairs in parallel corpora of Arabic-English. This metric combines two techniques, one based on sentence length and the other based on compression code length. Experiments on sample test parallel Arabic-English corpora indicate the combination of these two techniques improves accuracy of the identification of satisfactory and unsatisfactory sentence pairs compared to sentence length and compression code length alone. The new method proposed in this research is effective at filtering noi","authors_text":"Saad Alkahtani, Wei Liu, William J. Teahan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T17:49:45Z","title":"A new hybrid metric for verifying parallel corpora of Arabic-English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.03752","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":"sha256:647cb6465fa9aa747075b887fe6a788c83a6f7b65685fd769d238da9cf53676e","target":"record","created_at":"2026-05-18T02:27:16Z","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":"f613e859d927f91666ffcbf1c23aee765a9e0aeef90ab31f9dec6324b5642a46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-02-12T17:49:45Z","title_canon_sha256":"886978630508d58b32f11fa804cdff9e7a88d8c5aa91578cc7dbc427256bb585"},"schema_version":"1.0","source":{"id":"1502.03752","kind":"arxiv","version":1}},"canonical_sha256":"16953a28dd8ce47edd21157020e31b81f374235f468c09a28fbff6e28794e5ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16953a28dd8ce47edd21157020e31b81f374235f468c09a28fbff6e28794e5ce","first_computed_at":"2026-05-18T02:27:16.806910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:27:16.806910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b9KO8J9YZZgMxmHqqAVgsHYlNOgjHx7bMv4P3XfHlVqmoHfj1ZMMeB4C/NykhoKpz6IfIGn2IdkIDcygQm0DCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:27:16.807621Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.03752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:647cb6465fa9aa747075b887fe6a788c83a6f7b65685fd769d238da9cf53676e","sha256:a0ad87f550f45be100e5e1a6d9d32b4082a53d4d1250ad87bdd8a1e7a335e732"],"state_sha256":"666c55e0dfb84b7b18654fb42273a9269303c6931b8c9bade49c7990b4f9dc73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XwSm0/kQbORIh01d4ym7r+8zuMRrHuh9oORwChQzeEt5hYhZXnYLvJLdpO7mRHBW9JYgt2N2TBddrjvXVLwrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T09:59:03.273245Z","bundle_sha256":"74f9134274b61f0c6a22a3ef75614c8cfc5af8934a74c3ea88595b3bdb0de716"}}