{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T5WJQGDHZDAWJJFO4SA4AGEHDB","short_pith_number":"pith:T5WJQGDH","schema_version":"1.0","canonical_sha256":"9f6c981867c8c164a4aee481c01887186a7979b04f7c301b27d30400a0c6af17","source":{"kind":"arxiv","id":"2206.03281","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Houxing Ren, Linjun Shou, Ming Gong, Nan Duan, Ning Wu, Yaobo Liang","submitted_at":"2022-06-07T13:26:38Z","abstract_excerpt":"Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called contrastive context prediction~(CCP) to learn sentence representation by modeling sentence level contextual relation. By pushing the embedding of sentences in a local context closer and pushing random negative samples away, different languages could form isomorphic structure, then sentence pairs in two different languages will be automatically aligned. Our experim"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.03281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-07T13:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"b928b234507bd710218faa51ccebd696cc4375e312a150e0d30a0698908a25de","abstract_canon_sha256":"ee25f73acfc6860306b8932a7c63c4e8a1db74b7d6e4c703dc8dd6f0b55d045f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:41.033087Z","signature_b64":"rb9+OjNmHggkqSqAeoXMwo8sT2UJkMo+gknSWPMqHQHtSNireei+T8RLdi3VP8XF3huGF7Fz3ueX4FIopq55BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f6c981867c8c164a4aee481c01887186a7979b04f7c301b27d30400a0c6af17","last_reissued_at":"2026-07-05T04:29:41.032715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:41.032715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Houxing Ren, Linjun Shou, Ming Gong, Nan Duan, Ning Wu, Yaobo Liang","submitted_at":"2022-06-07T13:26:38Z","abstract_excerpt":"Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called contrastive context prediction~(CCP) to learn sentence representation by modeling sentence level contextual relation. By pushing the embedding of sentences in a local context closer and pushing random negative samples away, different languages could form isomorphic structure, then sentence pairs in two different languages will be automatically aligned. Our experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03281","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.03281/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.03281","created_at":"2026-07-05T04:29:41.032772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03281v1","created_at":"2026-07-05T04:29:41.032772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03281","created_at":"2026-07-05T04:29:41.032772+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5WJQGDHZDAW","created_at":"2026-07-05T04:29:41.032772+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5WJQGDHZDAWJJFO","created_at":"2026-07-05T04:29:41.032772+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5WJQGDH","created_at":"2026-07-05T04:29:41.032772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB","json":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB.json","graph_json":"https://pith.science/api/pith-number/T5WJQGDHZDAWJJFO4SA4AGEHDB/graph.json","events_json":"https://pith.science/api/pith-number/T5WJQGDHZDAWJJFO4SA4AGEHDB/events.json","paper":"https://pith.science/paper/T5WJQGDH"},"agent_actions":{"view_html":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB","download_json":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB.json","view_paper":"https://pith.science/paper/T5WJQGDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03281&json=true","fetch_graph":"https://pith.science/api/pith-number/T5WJQGDHZDAWJJFO4SA4AGEHDB/graph.json","fetch_events":"https://pith.science/api/pith-number/T5WJQGDHZDAWJJFO4SA4AGEHDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/action/storage_attestation","attest_author":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/action/author_attestation","sign_citation":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/action/citation_signature","submit_replication":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/action/replication_record"}},"created_at":"2026-07-05T04:29:41.032772+00:00","updated_at":"2026-07-05T04:29:41.032772+00:00"}