{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CAN4FTOIYGQPYLRB5HC327VGUQ","short_pith_number":"pith:CAN4FTOI","canonical_record":{"source":{"id":"2302.01626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T09:54:27Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"dde55a0e05a56a1c76f5ffb38b82d97f3109889d0abe0364bea8f863bc3bc73f","abstract_canon_sha256":"c2eab1f99b7adbf2a00ac4d1c283ad36d6ef69c3f96023bafa371d9cd164f5ff"},"schema_version":"1.0"},"canonical_sha256":"101bc2cdc8c1a0fc2e21e9c5bd7ea6a43c0e1814c322089c614bf02bce6e048d","source":{"kind":"arxiv","id":"2302.01626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01626","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01626v2","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01626","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"CAN4FTOIYGQP","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"CAN4FTOIYGQPYLRB","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"CAN4FTOI","created_at":"2026-07-05T12:05:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CAN4FTOIYGQPYLRB5HC327VGUQ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.01626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T09:54:27Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"dde55a0e05a56a1c76f5ffb38b82d97f3109889d0abe0364bea8f863bc3bc73f","abstract_canon_sha256":"c2eab1f99b7adbf2a00ac4d1c283ad36d6ef69c3f96023bafa371d9cd164f5ff"},"schema_version":"1.0"},"canonical_sha256":"101bc2cdc8c1a0fc2e21e9c5bd7ea6a43c0e1814c322089c614bf02bce6e048d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:05.974729Z","signature_b64":"W51jYdJGBaUogKYObyzBzmgAo7NJHkg3o+dYRa+Jx+WSjtqeqeRnDON305OM99phbI4dLDex3f7Hn1biEyQBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"101bc2cdc8c1a0fc2e21e9c5bd7ea6a43c0e1814c322089c614bf02bce6e048d","last_reissued_at":"2026-07-05T12:05:05.974260Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:05.974260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.01626","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/rJ/BlC8IjknWuAw98QGZCgJW2nopo/y+IUx2Ffg8pdFNCCbVC3dE7W10mllWwUFlmx4w1BsHKqgBlw1IPQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:34:14.974527Z"},"content_sha256":"0a52c23768d4a0a9ec9c77c42eac57f221ec5494a94006de27aaa30ce1ffe23a","schema_version":"1.0","event_id":"sha256:0a52c23768d4a0a9ec9c77c42eac57f221ec5494a94006de27aaa30ce1ffe23a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CAN4FTOIYGQPYLRB5HC327VGUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Daxin Jiang, Ming Gong, Nan Duan, Shunyu Zhang, Yaobo Liang","submitted_at":"2023-02-03T09:54:27Z","abstract_excerpt":"Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for cross-lingual retrieval is still unexplored. Motivated by an observation that the sentences in parallel documents are approximately in the same order, which is universal across languages, we propose to model this sequential sentence relation to facilitate cross-lingual representation learning. Specifically, we propose a multilingual PLM called masked sentenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01626","kind":"arxiv","version":2},"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/2302.01626/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":"2026-07-05T12:05:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SgJ0m4gqtf0iPZZ7KymED2pkja19nVjQnGJqV3GnpgtwmCdfoC3mLOM03logWgdeW88zyTHBesMrvFTXMvrTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:34:14.975018Z"},"content_sha256":"8d5ac843ac0803f970cc6a01c1d6ecdf642f34dbbc3837a2f83407295f04f250","schema_version":"1.0","event_id":"sha256:8d5ac843ac0803f970cc6a01c1d6ecdf642f34dbbc3837a2f83407295f04f250"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CAN4FTOIYGQPYLRB5HC327VGUQ/bundle.json","state_url":"https://pith.science/pith/CAN4FTOIYGQPYLRB5HC327VGUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CAN4FTOIYGQPYLRB5HC327VGUQ/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":"2026-08-05T09:34:14Z","links":{"resolver":"https://pith.science/pith/CAN4FTOIYGQPYLRB5HC327VGUQ","bundle":"https://pith.science/pith/CAN4FTOIYGQPYLRB5HC327VGUQ/bundle.json","state":"https://pith.science/pith/CAN4FTOIYGQPYLRB5HC327VGUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CAN4FTOIYGQPYLRB5HC327VGUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CAN4FTOIYGQPYLRB5HC327VGUQ","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":"c2eab1f99b7adbf2a00ac4d1c283ad36d6ef69c3f96023bafa371d9cd164f5ff","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T09:54:27Z","title_canon_sha256":"dde55a0e05a56a1c76f5ffb38b82d97f3109889d0abe0364bea8f863bc3bc73f"},"schema_version":"1.0","source":{"id":"2302.01626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01626","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01626v2","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01626","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"CAN4FTOIYGQP","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"CAN4FTOIYGQPYLRB","created_at":"2026-07-05T12:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"CAN4FTOI","created_at":"2026-07-05T12:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:8d5ac843ac0803f970cc6a01c1d6ecdf642f34dbbc3837a2f83407295f04f250","target":"graph","created_at":"2026-07-05T12:05:05Z","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/2302.01626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently multi-lingual pre-trained language models (PLM) such as mBERT and XLM-R have achieved impressive strides in cross-lingual dense retrieval. Despite its successes, they are general-purpose PLM while the multilingual PLM tailored for cross-lingual retrieval is still unexplored. Motivated by an observation that the sentences in parallel documents are approximately in the same order, which is universal across languages, we propose to model this sequential sentence relation to facilitate cross-lingual representation learning. Specifically, we propose a multilingual PLM called masked sentenc","authors_text":"Daxin Jiang, Ming Gong, Nan Duan, Shunyu Zhang, Yaobo Liang","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T09:54:27Z","title":"Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01626","kind":"arxiv","version":2},"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":"sha256:0a52c23768d4a0a9ec9c77c42eac57f221ec5494a94006de27aaa30ce1ffe23a","target":"record","created_at":"2026-07-05T12:05:05Z","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":"c2eab1f99b7adbf2a00ac4d1c283ad36d6ef69c3f96023bafa371d9cd164f5ff","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-03T09:54:27Z","title_canon_sha256":"dde55a0e05a56a1c76f5ffb38b82d97f3109889d0abe0364bea8f863bc3bc73f"},"schema_version":"1.0","source":{"id":"2302.01626","kind":"arxiv","version":2}},"canonical_sha256":"101bc2cdc8c1a0fc2e21e9c5bd7ea6a43c0e1814c322089c614bf02bce6e048d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"101bc2cdc8c1a0fc2e21e9c5bd7ea6a43c0e1814c322089c614bf02bce6e048d","first_computed_at":"2026-07-05T12:05:05.974260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:05.974260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W51jYdJGBaUogKYObyzBzmgAo7NJHkg3o+dYRa+Jx+WSjtqeqeRnDON305OM99phbI4dLDex3f7Hn1biEyQBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:05.974729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a52c23768d4a0a9ec9c77c42eac57f221ec5494a94006de27aaa30ce1ffe23a","sha256:8d5ac843ac0803f970cc6a01c1d6ecdf642f34dbbc3837a2f83407295f04f250"],"state_sha256":"3bfb2e80eadf8c0040cbe7d84a135cb68e5725df5a1c4584cd11a1fbe3c8e137"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kSnBygo5MF3h4sUPA4sF+HgyCwfjIOPzIRuL0Fa036bxwQZkKQ4g4NwdUhIM7N1EHrDwYMTZ/0zWYehWCXlmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:34:14.978458Z","bundle_sha256":"e915cead405c7c93e70cb798b6c88180b931896fb73bc6cb60fce0eebe8e44a2"}}