{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:MXZREOCHUDZL5H7T35KYSGJ6V4","short_pith_number":"pith:MXZREOCH","canonical_record":{"source":{"id":"1401.5674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-18T21:11:30Z","cross_cats_sorted":[],"title_canon_sha256":"0e310a7f8a56979d86f258202a9e7a14dacfe3b259745cc6b430909fc15c6889","abstract_canon_sha256":"5cff13c26293aacce87c5a8fdde7d415e1d649efad009dbfe550d258f8ae0b45"},"schema_version":"1.0"},"canonical_sha256":"65f3123847a0f2be9ff3df5589193eaf029fb82d8824925751ed79af9ee28864","source":{"kind":"arxiv","id":"1401.5674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.5674","created_at":"2026-05-18T03:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"1401.5674v1","created_at":"2026-05-18T03:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.5674","created_at":"2026-05-18T03:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"MXZREOCHUDZL","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"MXZREOCHUDZL5H7T","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"MXZREOCH","created_at":"2026-05-18T12:28:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:MXZREOCHUDZL5H7T35KYSGJ6V4","target":"record","payload":{"canonical_record":{"source":{"id":"1401.5674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-18T21:11:30Z","cross_cats_sorted":[],"title_canon_sha256":"0e310a7f8a56979d86f258202a9e7a14dacfe3b259745cc6b430909fc15c6889","abstract_canon_sha256":"5cff13c26293aacce87c5a8fdde7d415e1d649efad009dbfe550d258f8ae0b45"},"schema_version":"1.0"},"canonical_sha256":"65f3123847a0f2be9ff3df5589193eaf029fb82d8824925751ed79af9ee28864","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:01:25.010914Z","signature_b64":"JQAgbnTnu3s2MKIElSeNcX9zd1k7nv/8dEDcAckwAdYOJCDTrQ+1kXec3+xOX0K718YtyPGM3jp5n8OfrR7yDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f3123847a0f2be9ff3df5589193eaf029fb82d8824925751ed79af9ee28864","last_reissued_at":"2026-05-18T03:01:25.010102Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:01:25.010102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1401.5674","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":"2026-05-18T03:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WAzKTwJrCRwENq3hfGq/SxvZmYgy3Pb3j+A+YkuN7vWFYyVMVwK3mw2YhDiHx8i6vMMeMwuzCvyorNXajZJlCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T06:13:26.346270Z"},"content_sha256":"8838e99c0d4529ce19209a422d691db5b5520326bb1427ed98825f34bd53e793","schema_version":"1.0","event_id":"sha256:8838e99c0d4529ce19209a422d691db5b5520326bb1427ed98825f34bd53e793"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:MXZREOCHUDZL5H7T35KYSGJ6V4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalized Biwords for Bitext Compression and Translation Spotting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Felipe S\\'anchez-Mart\\'inez, Joaquin Adiego, Miguel A. Mart\\'inez-Prieto, Rafael C. Carrasco","submitted_at":"2014-01-18T21:11:30Z","abstract_excerpt":"Large bilingual parallel texts (also known as bitexts) are usually stored in a compressed form, and previous work has shown that they can be more efficiently compressed if the fact that the two texts are mutual translations is exploited. For example, a bitext can be seen as a sequence of biwords ---pairs of parallel words with a high probability of co-occurrence--- that can be used as an intermediate representation in the compression process.  However, the simple biword approach described in the literature can only exploit one-to-one word alignments and cannot tackle the reordering of words. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.5674","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":"2026-05-18T03:01:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HaeyarcjShCoZHAq6vgB0w24G5pnvdrXpmpmEcKtVOsiTLQURYtk8gzcGOldv4LHIWbhigJETw+oArEcmdZxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T06:13:26.346860Z"},"content_sha256":"555d9ae7ed6d6fdcf3341cb88ffb037aefd73d5fcd964edaffaab2c9836d007e","schema_version":"1.0","event_id":"sha256:555d9ae7ed6d6fdcf3341cb88ffb037aefd73d5fcd964edaffaab2c9836d007e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXZREOCHUDZL5H7T35KYSGJ6V4/bundle.json","state_url":"https://pith.science/pith/MXZREOCHUDZL5H7T35KYSGJ6V4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXZREOCHUDZL5H7T35KYSGJ6V4/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":"2026-06-28T06:13:26Z","links":{"resolver":"https://pith.science/pith/MXZREOCHUDZL5H7T35KYSGJ6V4","bundle":"https://pith.science/pith/MXZREOCHUDZL5H7T35KYSGJ6V4/bundle.json","state":"https://pith.science/pith/MXZREOCHUDZL5H7T35KYSGJ6V4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXZREOCHUDZL5H7T35KYSGJ6V4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:MXZREOCHUDZL5H7T35KYSGJ6V4","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":"5cff13c26293aacce87c5a8fdde7d415e1d649efad009dbfe550d258f8ae0b45","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-18T21:11:30Z","title_canon_sha256":"0e310a7f8a56979d86f258202a9e7a14dacfe3b259745cc6b430909fc15c6889"},"schema_version":"1.0","source":{"id":"1401.5674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1401.5674","created_at":"2026-05-18T03:01:25Z"},{"alias_kind":"arxiv_version","alias_value":"1401.5674v1","created_at":"2026-05-18T03:01:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1401.5674","created_at":"2026-05-18T03:01:25Z"},{"alias_kind":"pith_short_12","alias_value":"MXZREOCHUDZL","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_16","alias_value":"MXZREOCHUDZL5H7T","created_at":"2026-05-18T12:28:38Z"},{"alias_kind":"pith_short_8","alias_value":"MXZREOCH","created_at":"2026-05-18T12:28:38Z"}],"graph_snapshots":[{"event_id":"sha256:555d9ae7ed6d6fdcf3341cb88ffb037aefd73d5fcd964edaffaab2c9836d007e","target":"graph","created_at":"2026-05-18T03:01:25Z","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":"Large bilingual parallel texts (also known as bitexts) are usually stored in a compressed form, and previous work has shown that they can be more efficiently compressed if the fact that the two texts are mutual translations is exploited. For example, a bitext can be seen as a sequence of biwords ---pairs of parallel words with a high probability of co-occurrence--- that can be used as an intermediate representation in the compression process.  However, the simple biword approach described in the literature can only exploit one-to-one word alignments and cannot tackle the reordering of words. W","authors_text":"Felipe S\\'anchez-Mart\\'inez, Joaquin Adiego, Miguel A. Mart\\'inez-Prieto, Rafael C. Carrasco","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-18T21:11:30Z","title":"Generalized Biwords for Bitext Compression and Translation Spotting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1401.5674","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":"sha256:8838e99c0d4529ce19209a422d691db5b5520326bb1427ed98825f34bd53e793","target":"record","created_at":"2026-05-18T03:01:25Z","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":"5cff13c26293aacce87c5a8fdde7d415e1d649efad009dbfe550d258f8ae0b45","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-01-18T21:11:30Z","title_canon_sha256":"0e310a7f8a56979d86f258202a9e7a14dacfe3b259745cc6b430909fc15c6889"},"schema_version":"1.0","source":{"id":"1401.5674","kind":"arxiv","version":1}},"canonical_sha256":"65f3123847a0f2be9ff3df5589193eaf029fb82d8824925751ed79af9ee28864","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65f3123847a0f2be9ff3df5589193eaf029fb82d8824925751ed79af9ee28864","first_computed_at":"2026-05-18T03:01:25.010102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:01:25.010102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JQAgbnTnu3s2MKIElSeNcX9zd1k7nv/8dEDcAckwAdYOJCDTrQ+1kXec3+xOX0K718YtyPGM3jp5n8OfrR7yDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:01:25.010914Z","signed_message":"canonical_sha256_bytes"},"source_id":"1401.5674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8838e99c0d4529ce19209a422d691db5b5520326bb1427ed98825f34bd53e793","sha256:555d9ae7ed6d6fdcf3341cb88ffb037aefd73d5fcd964edaffaab2c9836d007e"],"state_sha256":"4bfd67d17b65a83f2649fe281f9f0dd8643eac7b89defa87f7a511d5a5f8b045"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bhWuaczZBKlPeYjb83V9Qw0EtFDti7/QHtX+VFvLCcNJmqTnxpoh+mY2XsAVevzXTQ0Hnlxlnleif0OBKA6LDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T06:13:26.348593Z","bundle_sha256":"73a109fedcd1c0ff64ad030a8ac128243fd2334cb2171f3debb78fbe46aa121b"}}