{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F3673YJS3C4FSDLD7FPZKTO2RQ","short_pith_number":"pith:F3673YJS","schema_version":"1.0","canonical_sha256":"2efdfde132d8b8590d63f95f954dda8c3e91e9466761301e9c0331f7b4596adf","source":{"kind":"arxiv","id":"2409.17777","version":4},"attestation_state":"computed","paper":{"title":"Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Deval Mehta, Kshitij Jadhav, Pranamya Kulkarni, Raghav Singhal, Raja Kumar","submitted_at":"2024-09-26T12:15:13Z","abstract_excerpt":"Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise associations. We propose M3CoL, a Multimodal Mixup Contrastive Learning approach to capture nuanced shared relations inherent in multimodal data. Our key contribution is a Mixup-based contrastive loss that learns robust representations by aligning mixed samples from one modality with their corresponding samples from other modalities thereby capturing shared relations b"},"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":"2409.17777","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T12:15:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0cf48d3fce262489e3a289e40c17ac45da675b2b89aa1fe4be73b8021b2e7ed","abstract_canon_sha256":"b6a8522b57b49299801a976f8262600ef8e94a7c25c2564c3abc3cce2fded9ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:02.035113Z","signature_b64":"dfHE/tKxQulZwO6Kz8zivB+tmcIVz52CWqWoURJNjSwV6wzYXK5gEQ4Cvj1Q55FYeyT8LXvgl5oDAMIscSQwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2efdfde132d8b8590d63f95f954dda8c3e91e9466761301e9c0331f7b4596adf","last_reissued_at":"2026-07-05T11:29:02.034581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:02.034581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Deval Mehta, Kshitij Jadhav, Pranamya Kulkarni, Raghav Singhal, Raja Kumar","submitted_at":"2024-09-26T12:15:13Z","abstract_excerpt":"Deep multimodal learning has shown remarkable success by leveraging contrastive learning to capture explicit one-to-one relations across modalities. However, real-world data often exhibits shared relations beyond simple pairwise associations. We propose M3CoL, a Multimodal Mixup Contrastive Learning approach to capture nuanced shared relations inherent in multimodal data. Our key contribution is a Mixup-based contrastive loss that learns robust representations by aligning mixed samples from one modality with their corresponding samples from other modalities thereby capturing shared relations b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17777","kind":"arxiv","version":4},"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/2409.17777/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":"2409.17777","created_at":"2026-07-05T11:29:02.034638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.17777v4","created_at":"2026-07-05T11:29:02.034638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17777","created_at":"2026-07-05T11:29:02.034638+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3673YJS3C4F","created_at":"2026-07-05T11:29:02.034638+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3673YJS3C4FSDLD","created_at":"2026-07-05T11:29:02.034638+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3673YJS","created_at":"2026-07-05T11:29:02.034638+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/F3673YJS3C4FSDLD7FPZKTO2RQ","json":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ.json","graph_json":"https://pith.science/api/pith-number/F3673YJS3C4FSDLD7FPZKTO2RQ/graph.json","events_json":"https://pith.science/api/pith-number/F3673YJS3C4FSDLD7FPZKTO2RQ/events.json","paper":"https://pith.science/paper/F3673YJS"},"agent_actions":{"view_html":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ","download_json":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ.json","view_paper":"https://pith.science/paper/F3673YJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.17777&json=true","fetch_graph":"https://pith.science/api/pith-number/F3673YJS3C4FSDLD7FPZKTO2RQ/graph.json","fetch_events":"https://pith.science/api/pith-number/F3673YJS3C4FSDLD7FPZKTO2RQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ/action/storage_attestation","attest_author":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ/action/author_attestation","sign_citation":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ/action/citation_signature","submit_replication":"https://pith.science/pith/F3673YJS3C4FSDLD7FPZKTO2RQ/action/replication_record"}},"created_at":"2026-07-05T11:29:02.034638+00:00","updated_at":"2026-07-05T11:29:02.034638+00:00"}