{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q6KRBPDOEM5POCQF2MATMIACKX","short_pith_number":"pith:Q6KRBPDO","schema_version":"1.0","canonical_sha256":"879510bc6e233af70a05d30136200255cfab548aff4d044bdbb78f8fb3103813","source":{"kind":"arxiv","id":"2303.12419","version":2},"attestation_state":"computed","paper":{"title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxun Yao, Kai Wang, Min Xu, Shuo Yang, Tongliang Liu, Yang You, Zhaopan Xu","submitted_at":"2023-03-22T09:33:50Z","abstract_excerpt":"As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, massive and correctly aligned data pairs are required for model training. However, unlike unimodal datasets, multimodal datasets are extremely harder to collect and annotate precisely. As an alternative, the co-occurred data pairs (e.g., image-text pairs) collected from the Internet have been widely exploited in the area. Unfortunately, the cheaply collected dataset unavoidably contains many mismatched data pairs, which "},"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":"2303.12419","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-22T09:33:50Z","cross_cats_sorted":[],"title_canon_sha256":"31dca5886cf8f5ace04381207d4167b0f1995a7f99a5b1527b3222acc9a6fa48","abstract_canon_sha256":"f014761ee87c10e213c50fd03f7883802e40b367a3f5408926b42302a0da2e03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:38.454843Z","signature_b64":"IV40uizXPdk18DsV8c/t+KT+//eoIckmpaH8e8B2FHnbVRQ6wcu6iGR1EP6fYh036v9EIYJWp89twcmKBascCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"879510bc6e233af70a05d30136200255cfab548aff4d044bdbb78f8fb3103813","last_reissued_at":"2026-07-05T06:18:38.454397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:38.454397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxun Yao, Kai Wang, Min Xu, Shuo Yang, Tongliang Liu, Yang You, Zhaopan Xu","submitted_at":"2023-03-22T09:33:50Z","abstract_excerpt":"As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space. To achieve this, massive and correctly aligned data pairs are required for model training. However, unlike unimodal datasets, multimodal datasets are extremely harder to collect and annotate precisely. As an alternative, the co-occurred data pairs (e.g., image-text pairs) collected from the Internet have been widely exploited in the area. Unfortunately, the cheaply collected dataset unavoidably contains many mismatched data pairs, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.12419","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/2303.12419/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":"2303.12419","created_at":"2026-07-05T06:18:38.454455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.12419v2","created_at":"2026-07-05T06:18:38.454455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.12419","created_at":"2026-07-05T06:18:38.454455+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6KRBPDOEM5P","created_at":"2026-07-05T06:18:38.454455+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6KRBPDOEM5POCQF","created_at":"2026-07-05T06:18:38.454455+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6KRBPDO","created_at":"2026-07-05T06:18:38.454455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":274,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":252,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":274,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX","json":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX.json","graph_json":"https://pith.science/api/pith-number/Q6KRBPDOEM5POCQF2MATMIACKX/graph.json","events_json":"https://pith.science/api/pith-number/Q6KRBPDOEM5POCQF2MATMIACKX/events.json","paper":"https://pith.science/paper/Q6KRBPDO"},"agent_actions":{"view_html":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX","download_json":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX.json","view_paper":"https://pith.science/paper/Q6KRBPDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.12419&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6KRBPDOEM5POCQF2MATMIACKX/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6KRBPDOEM5POCQF2MATMIACKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX/action/storage_attestation","attest_author":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX/action/author_attestation","sign_citation":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX/action/citation_signature","submit_replication":"https://pith.science/pith/Q6KRBPDOEM5POCQF2MATMIACKX/action/replication_record"}},"created_at":"2026-07-05T06:18:38.454455+00:00","updated_at":"2026-07-05T06:18:38.454455+00:00"}