{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZVCZAWGT6VMD3AAAR6KCIUWRCV","short_pith_number":"pith:ZVCZAWGT","canonical_record":{"source":{"id":"2303.14979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-27T08:22:21Z","cross_cats_sorted":[],"title_canon_sha256":"ead2976d7bf0060d152bcf3e34c868cfe662418a48e15562ad09044e48fb3bd3","abstract_canon_sha256":"b1a3e24c89d6740404eaecd71802f2647b3e2b88ceb76f08f0ee69ff25056ce1"},"schema_version":"1.0"},"canonical_sha256":"cd459058d3f5583d80008f942452d11541a4abc697e7a98cd484950057df1b66","source":{"kind":"arxiv","id":"2303.14979","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14979","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14979v1","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14979","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZVCZAWGT6VMD","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZVCZAWGT6VMD3AAA","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZVCZAWGT","created_at":"2026-07-05T05:54:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZVCZAWGT6VMD3AAAR6KCIUWRCV","target":"record","payload":{"canonical_record":{"source":{"id":"2303.14979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-27T08:22:21Z","cross_cats_sorted":[],"title_canon_sha256":"ead2976d7bf0060d152bcf3e34c868cfe662418a48e15562ad09044e48fb3bd3","abstract_canon_sha256":"b1a3e24c89d6740404eaecd71802f2647b3e2b88ceb76f08f0ee69ff25056ce1"},"schema_version":"1.0"},"canonical_sha256":"cd459058d3f5583d80008f942452d11541a4abc697e7a98cd484950057df1b66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:57.932396Z","signature_b64":"Di30Vq2uK33PBY31b2zHIndTkHfv1vh8ZcXoIdpZ0SUMfNl7pjZUGL56C3eySlFw5dycgZIh2hOkmzUiQBv7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd459058d3f5583d80008f942452d11541a4abc697e7a98cd484950057df1b66","last_reissued_at":"2026-07-05T05:54:57.931987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:57.931987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.14979","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":"2026-07-05T05:54:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SxSUf4YRtGwIz/AvlucBj9YiNzwucKQS7W+1q0vK0i9dVePsqtl+07whGElMwOPcrJ5eUjgzn7FKPPnRVCP6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T08:39:05.759292Z"},"content_sha256":"9ccc5b09274de7f8253dbfc58e7a92bd5039a25ab352dc5e7f3b11dccfade62b","schema_version":"1.0","event_id":"sha256:9ccc5b09274de7f8253dbfc58e7a92bd5039a25ab352dc5e7f3b11dccfade62b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZVCZAWGT6VMD3AAAR6KCIUWRCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Daxin Jiang, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Ning Wu","submitted_at":"2023-03-27T08:22:21Z","abstract_excerpt":"Recent multilingual pre-trained models have shown better performance in various multilingual tasks. However, these models perform poorly on multilingual retrieval tasks due to lacking multilingual training data. In this paper, we propose to mine and generate self-supervised training data based on a large-scale unlabeled corpus. We carefully design a mining method which combines the sparse and dense models to mine the relevance of unlabeled queries and passages. And we introduce a query generator to generate more queries in target languages for unlabeled passages. Through extensive experiments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14979","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/2303.14979/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":"2026-07-05T05:54:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g21bVF2zWEDxygTi+B/ikIDk11Z+nG2KCePP+REoAOHhuTZmECd8liYH/DmzaZi7MW2hOFZwjCU0XFrv7FzGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T08:39:05.759803Z"},"content_sha256":"8595c4bf4545c28192410094422b079698be8e471773147bc147ea1f71f824fa","schema_version":"1.0","event_id":"sha256:8595c4bf4545c28192410094422b079698be8e471773147bc147ea1f71f824fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV/bundle.json","state_url":"https://pith.science/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV/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":"2026-07-13T08:39:05Z","links":{"resolver":"https://pith.science/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV","bundle":"https://pith.science/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV/bundle.json","state":"https://pith.science/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVCZAWGT6VMD3AAAR6KCIUWRCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZVCZAWGT6VMD3AAAR6KCIUWRCV","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":"b1a3e24c89d6740404eaecd71802f2647b3e2b88ceb76f08f0ee69ff25056ce1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-27T08:22:21Z","title_canon_sha256":"ead2976d7bf0060d152bcf3e34c868cfe662418a48e15562ad09044e48fb3bd3"},"schema_version":"1.0","source":{"id":"2303.14979","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14979","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14979v1","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14979","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZVCZAWGT6VMD","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZVCZAWGT6VMD3AAA","created_at":"2026-07-05T05:54:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZVCZAWGT","created_at":"2026-07-05T05:54:57Z"}],"graph_snapshots":[{"event_id":"sha256:8595c4bf4545c28192410094422b079698be8e471773147bc147ea1f71f824fa","target":"graph","created_at":"2026-07-05T05:54:57Z","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/2303.14979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent multilingual pre-trained models have shown better performance in various multilingual tasks. However, these models perform poorly on multilingual retrieval tasks due to lacking multilingual training data. In this paper, we propose to mine and generate self-supervised training data based on a large-scale unlabeled corpus. We carefully design a mining method which combines the sparse and dense models to mine the relevance of unlabeled queries and passages. And we introduce a query generator to generate more queries in target languages for unlabeled passages. Through extensive experiments ","authors_text":"Daxin Jiang, Houxing Ren, Jian Pei, Linjun Shou, Ming Gong, Ning Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-27T08:22:21Z","title":"Lexicon-Enhanced Self-Supervised Training for Multilingual Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14979","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":"sha256:9ccc5b09274de7f8253dbfc58e7a92bd5039a25ab352dc5e7f3b11dccfade62b","target":"record","created_at":"2026-07-05T05:54:57Z","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":"b1a3e24c89d6740404eaecd71802f2647b3e2b88ceb76f08f0ee69ff25056ce1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-27T08:22:21Z","title_canon_sha256":"ead2976d7bf0060d152bcf3e34c868cfe662418a48e15562ad09044e48fb3bd3"},"schema_version":"1.0","source":{"id":"2303.14979","kind":"arxiv","version":1}},"canonical_sha256":"cd459058d3f5583d80008f942452d11541a4abc697e7a98cd484950057df1b66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd459058d3f5583d80008f942452d11541a4abc697e7a98cd484950057df1b66","first_computed_at":"2026-07-05T05:54:57.931987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:57.931987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Di30Vq2uK33PBY31b2zHIndTkHfv1vh8ZcXoIdpZ0SUMfNl7pjZUGL56C3eySlFw5dycgZIh2hOkmzUiQBv7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:57.932396Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14979","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ccc5b09274de7f8253dbfc58e7a92bd5039a25ab352dc5e7f3b11dccfade62b","sha256:8595c4bf4545c28192410094422b079698be8e471773147bc147ea1f71f824fa"],"state_sha256":"1b16ac5ed120063161de47e8f8907667532278dfd784b854fed055af721515aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2tcIBV+Qy+1nYf5UhL3gYf3fbbbQnvbr6uqmkYlGReENRZv+t/ml1D3+VCULF7ORmAOKtXcoUrSo9lRIgK7Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T08:39:05.762083Z","bundle_sha256":"f4eeda4245686f625dac0570ea348a2654b287e8f023d4d2d17157dfc262797a"}}