{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:T5WJQGDHZDAWJJFO4SA4AGEHDB","short_pith_number":"pith:T5WJQGDH","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"},"canonical_sha256":"9f6c981867c8c164a4aee481c01887186a7979b04f7c301b27d30400a0c6af17","source":{"kind":"arxiv","id":"2206.03281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03281","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03281v1","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03281","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"T5WJQGDHZDAW","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"T5WJQGDHZDAWJJFO","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"T5WJQGDH","created_at":"2026-07-05T04:29:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:T5WJQGDHZDAWJJFO4SA4AGEHDB","target":"record","payload":{"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"},"canonical_sha256":"9f6c981867c8c164a4aee481c01887186a7979b04f7c301b27d30400a0c6af17","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"},"source_kind":"arxiv","source_id":"2206.03281","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":"2026-07-05T04:29:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5WO3JdNB3IsP8jOGG+WZh+UgldvaTZrNkWKZG1bsvSy+nWvOeKotLu2Qp59HuyvpJ+LFi9XTzdONkHgaoWwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:06.363977Z"},"content_sha256":"dcda637585c6709efb0de763bd04aecbb31b2f8ab3292f7e2bf5ccf6ef5cb3b6","schema_version":"1.0","event_id":"sha256:dcda637585c6709efb0de763bd04aecbb31b2f8ab3292f7e2bf5ccf6ef5cb3b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:T5WJQGDHZDAWJJFO4SA4AGEHDB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:29:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEiXjY7/IDv3MRduFOReGzTcaX1nzCSCvkb/xACiEGUt+jp7N3y6GjBPcTGr/PUP1CK1+IUQY/+qvQ/e0SAOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:05:06.364367Z"},"content_sha256":"0b81ed4b87132e1d80c772358ab1bfb43fb267c6eabbd1443091bd2da439b88d","schema_version":"1.0","event_id":"sha256:0b81ed4b87132e1d80c772358ab1bfb43fb267c6eabbd1443091bd2da439b88d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/bundle.json","state_url":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/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":"2026-07-07T10:05:06Z","links":{"resolver":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB","bundle":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/bundle.json","state":"https://pith.science/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5WJQGDHZDAWJJFO4SA4AGEHDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T5WJQGDHZDAWJJFO4SA4AGEHDB","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":"ee25f73acfc6860306b8932a7c63c4e8a1db74b7d6e4c703dc8dd6f0b55d045f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-07T13:26:38Z","title_canon_sha256":"b928b234507bd710218faa51ccebd696cc4375e312a150e0d30a0698908a25de"},"schema_version":"1.0","source":{"id":"2206.03281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.03281","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2206.03281v1","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03281","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"T5WJQGDHZDAW","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"T5WJQGDHZDAWJJFO","created_at":"2026-07-05T04:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"T5WJQGDH","created_at":"2026-07-05T04:29:41Z"}],"graph_snapshots":[{"event_id":"sha256:0b81ed4b87132e1d80c772358ab1bfb43fb267c6eabbd1443091bd2da439b88d","target":"graph","created_at":"2026-07-05T04:29:41Z","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/2206.03281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daxin Jiang, Houxing Ren, Linjun Shou, Ming Gong, Nan Duan, Ning Wu, Yaobo Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-07T13:26:38Z","title":"Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03281","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:dcda637585c6709efb0de763bd04aecbb31b2f8ab3292f7e2bf5ccf6ef5cb3b6","target":"record","created_at":"2026-07-05T04:29:41Z","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":"ee25f73acfc6860306b8932a7c63c4e8a1db74b7d6e4c703dc8dd6f0b55d045f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2022-06-07T13:26:38Z","title_canon_sha256":"b928b234507bd710218faa51ccebd696cc4375e312a150e0d30a0698908a25de"},"schema_version":"1.0","source":{"id":"2206.03281","kind":"arxiv","version":1}},"canonical_sha256":"9f6c981867c8c164a4aee481c01887186a7979b04f7c301b27d30400a0c6af17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f6c981867c8c164a4aee481c01887186a7979b04f7c301b27d30400a0c6af17","first_computed_at":"2026-07-05T04:29:41.032715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:41.032715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rb9+OjNmHggkqSqAeoXMwo8sT2UJkMo+gknSWPMqHQHtSNireei+T8RLdi3VP8XF3huGF7Fz3ueX4FIopq55BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:41.033087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.03281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcda637585c6709efb0de763bd04aecbb31b2f8ab3292f7e2bf5ccf6ef5cb3b6","sha256:0b81ed4b87132e1d80c772358ab1bfb43fb267c6eabbd1443091bd2da439b88d"],"state_sha256":"163eef4735205bc0a5369997602dc2a00c1a18dd7d31b387b2f07f21ab16bcd8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaisL451vY/U2+x9xn1GvdgmwA5OrbFQqZCH/vD7Nr2IWVTg11xogLg39G+3zISzMO2vYbMAjplXa7fN+CyvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:05:06.366285Z","bundle_sha256":"4a4c630876e5cb23b2408e77e8dc8601d4a1ad64f1ef1da9b0bc93d8e26996d5"}}