{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TEC32CILB7B2HNUCMROMHN4IZP","short_pith_number":"pith:TEC32CIL","canonical_record":{"source":{"id":"2509.09459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-11T13:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"506cb71e9eeb695c9d914e5f1c9ab9371deef3a571214366e3d721b09caba8ba","abstract_canon_sha256":"fa936a55d73127be23718976463ed67dd9e910a1f353c660342cc1d14b6cbbbc"},"schema_version":"1.0"},"canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","source":{"kind":"arxiv","id":"2509.09459","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09459","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09459v1","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09459","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"pith_short_12","alias_value":"TEC32CILB7B2","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"pith_short_16","alias_value":"TEC32CILB7B2HNUC","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"pith_short_8","alias_value":"TEC32CIL","created_at":"2026-07-05T12:09:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TEC32CILB7B2HNUCMROMHN4IZP","target":"record","payload":{"canonical_record":{"source":{"id":"2509.09459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-11T13:42:50Z","cross_cats_sorted":[],"title_canon_sha256":"506cb71e9eeb695c9d914e5f1c9ab9371deef3a571214366e3d721b09caba8ba","abstract_canon_sha256":"fa936a55d73127be23718976463ed67dd9e910a1f353c660342cc1d14b6cbbbc"},"schema_version":"1.0"},"canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:36.432008Z","signature_b64":"Iqii9PmOUFFQ/a3FFV+9Fqz25tnV/8RodLShvpLuzZpkTmzs5rGmEwz6exEs9Fqs1Obii/eZDSn3CX8Gh+8DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","last_reissued_at":"2026-07-05T12:09:36.431500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:36.431500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.09459","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":"2026-07-05T12:09:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FYLdNWiOWVWL0dPyFsHde54wZmt4VSkQC9JZGPm52gk3ZNI2ggoLwa0wBIfKhu/eBie5mqObBPK/GdpN4X0fCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:01:38.400157Z"},"content_sha256":"eb0012c526544da9caf6e1031994553a4f3b2199be4cd22323195a5887f4ae98","schema_version":"1.0","event_id":"sha256:eb0012c526544da9caf6e1031994553a4f3b2199be4cd22323195a5887f4ae98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TEC32CILB7B2HNUCMROMHN4IZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Data Utilization for Multilingual Dense Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Changhao Guan, Chao Huang, Fengran Mo, Jinan Xu, Kaiyu Huang, Xinyu Wang, Yufeng Chen, Zhenrui Yue","submitted_at":"2025-09-11T13:42:50Z","abstract_excerpt":"Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09459","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/2509.09459/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":"2026-07-05T12:09:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tcz0nJFCNUO0sVa1F5sYtg/R3JHp+QGtpiCJYrX1q5jaulkj82Hi6cdlHNY7tjHQh8kjJwdV2c+mZuxJrOZZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:01:38.400685Z"},"content_sha256":"ed5d58050a8c6c91047f37efb43ffeed4ef4f707fcd6242a8282aceff5ccf82c","schema_version":"1.0","event_id":"sha256:ed5d58050a8c6c91047f37efb43ffeed4ef4f707fcd6242a8282aceff5ccf82c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/bundle.json","state_url":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TEC32CILB7B2HNUCMROMHN4IZP/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":"2026-08-04T04:01:38Z","links":{"resolver":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP","bundle":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/bundle.json","state":"https://pith.science/pith/TEC32CILB7B2HNUCMROMHN4IZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TEC32CILB7B2HNUCMROMHN4IZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEC32CILB7B2HNUCMROMHN4IZP","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":"fa936a55d73127be23718976463ed67dd9e910a1f353c660342cc1d14b6cbbbc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-11T13:42:50Z","title_canon_sha256":"506cb71e9eeb695c9d914e5f1c9ab9371deef3a571214366e3d721b09caba8ba"},"schema_version":"1.0","source":{"id":"2509.09459","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09459","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09459v1","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09459","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"pith_short_12","alias_value":"TEC32CILB7B2","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"pith_short_16","alias_value":"TEC32CILB7B2HNUC","created_at":"2026-07-05T12:09:36Z"},{"alias_kind":"pith_short_8","alias_value":"TEC32CIL","created_at":"2026-07-05T12:09:36Z"}],"graph_snapshots":[{"event_id":"sha256:ed5d58050a8c6c91047f37efb43ffeed4ef4f707fcd6242a8282aceff5ccf82c","target":"graph","created_at":"2026-07-05T12:09:36Z","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/2509.09459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model architecture, we propose a method to boost data utilization for multilingual dense retrieval by obtainin","authors_text":"Changhao Guan, Chao Huang, Fengran Mo, Jinan Xu, Kaiyu Huang, Xinyu Wang, Yufeng Chen, Zhenrui Yue","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-11T13:42:50Z","title":"Boosting Data Utilization for Multilingual Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09459","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:eb0012c526544da9caf6e1031994553a4f3b2199be4cd22323195a5887f4ae98","target":"record","created_at":"2026-07-05T12:09:36Z","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":"fa936a55d73127be23718976463ed67dd9e910a1f353c660342cc1d14b6cbbbc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-09-11T13:42:50Z","title_canon_sha256":"506cb71e9eeb695c9d914e5f1c9ab9371deef3a571214366e3d721b09caba8ba"},"schema_version":"1.0","source":{"id":"2509.09459","kind":"arxiv","version":1}},"canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9905bd090b0fc3a3b682645cc3b788cbf32a498bf4354d6bc9a27773a55ed1d1","first_computed_at":"2026-07-05T12:09:36.431500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:36.431500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Iqii9PmOUFFQ/a3FFV+9Fqz25tnV/8RodLShvpLuzZpkTmzs5rGmEwz6exEs9Fqs1Obii/eZDSn3CX8Gh+8DBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:36.432008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09459","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb0012c526544da9caf6e1031994553a4f3b2199be4cd22323195a5887f4ae98","sha256:ed5d58050a8c6c91047f37efb43ffeed4ef4f707fcd6242a8282aceff5ccf82c"],"state_sha256":"3fca781cd416f3504d8e04ac6694742b8e65a5cd7cd06a9da7a69373beee4014"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"srZgM25zWPsmNXxqoCj8adOZtBIRfKSYeqRawxSF36iakFh2tmxlL+2EqsEzZsrLaBDOsPew+hbo/q+AXDJqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:01:38.404007Z","bundle_sha256":"7325af0f9dd0ce885c6178eb645d6ffb8d61e1e73b9edead2bd28ee96f7cc59c"}}