{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RZJSHAL3HODH64FZLBIQEIHTU4","short_pith_number":"pith:RZJSHAL3","schema_version":"1.0","canonical_sha256":"8e5323817b3b867f70b958510220f3a72d018adceb9b2d0fbd3204484a47cb73","source":{"kind":"arxiv","id":"2309.05300","version":3},"attestation_state":"computed","paper":{"title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenying Liu, Conrad M Albrecht, Nassim Ait Ali Braham, Xiao Xiang Zhu, Yi Wang, Zhitong Xiong","submitted_at":"2023-09-11T08:35:23Z","abstract_excerpt":"The increasing availability of multi-sensor data sparks wide interest in multimodal self-supervised learning. However, most existing approaches learn only common representations across modalities while ignoring intra-modal training and modality-unique representations. We propose Decoupling Common and Unique Representations (DeCUR), a simple yet effective method for multimodal self-supervised learning. By distinguishing inter- and intra-modal embeddings through multimodal redundancy reduction, DeCUR can integrate complementary information across different modalities. We evaluate DeCUR in three "},"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":"2309.05300","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T08:35:23Z","cross_cats_sorted":[],"title_canon_sha256":"f77e19ebd10ad1976ce55650ae627604105a630b066c6c42caee35132a19e6d6","abstract_canon_sha256":"7de17269d184fd1becfb152a7fd124ec5c2246a3ee702ac814daf30cd71d6550"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:06.077925Z","signature_b64":"cV0D0cNgfTOtYhgjvqQcbM3haXBzFayetN8vmyZJfw3Ront7COOne3eQLFTV+SlTRCF2zSgIO6CM5esC/JZGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e5323817b3b867f70b958510220f3a72d018adceb9b2d0fbd3204484a47cb73","last_reissued_at":"2026-07-05T08:46:06.077447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:06.077447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Common and Unique Representations for Multimodal Self-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenying Liu, Conrad M Albrecht, Nassim Ait Ali Braham, Xiao Xiang Zhu, Yi Wang, Zhitong Xiong","submitted_at":"2023-09-11T08:35:23Z","abstract_excerpt":"The increasing availability of multi-sensor data sparks wide interest in multimodal self-supervised learning. However, most existing approaches learn only common representations across modalities while ignoring intra-modal training and modality-unique representations. We propose Decoupling Common and Unique Representations (DeCUR), a simple yet effective method for multimodal self-supervised learning. By distinguishing inter- and intra-modal embeddings through multimodal redundancy reduction, DeCUR can integrate complementary information across different modalities. We evaluate DeCUR in three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05300","kind":"arxiv","version":3},"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/2309.05300/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":"2309.05300","created_at":"2026-07-05T08:46:06.077504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05300v3","created_at":"2026-07-05T08:46:06.077504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05300","created_at":"2026-07-05T08:46:06.077504+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZJSHAL3HODH","created_at":"2026-07-05T08:46:06.077504+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZJSHAL3HODH64FZ","created_at":"2026-07-05T08:46:06.077504+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZJSHAL3","created_at":"2026-07-05T08:46:06.077504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.20380","citing_title":"TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4","json":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4.json","graph_json":"https://pith.science/api/pith-number/RZJSHAL3HODH64FZLBIQEIHTU4/graph.json","events_json":"https://pith.science/api/pith-number/RZJSHAL3HODH64FZLBIQEIHTU4/events.json","paper":"https://pith.science/paper/RZJSHAL3"},"agent_actions":{"view_html":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4","download_json":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4.json","view_paper":"https://pith.science/paper/RZJSHAL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05300&json=true","fetch_graph":"https://pith.science/api/pith-number/RZJSHAL3HODH64FZLBIQEIHTU4/graph.json","fetch_events":"https://pith.science/api/pith-number/RZJSHAL3HODH64FZLBIQEIHTU4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4/action/storage_attestation","attest_author":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4/action/author_attestation","sign_citation":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4/action/citation_signature","submit_replication":"https://pith.science/pith/RZJSHAL3HODH64FZLBIQEIHTU4/action/replication_record"}},"created_at":"2026-07-05T08:46:06.077504+00:00","updated_at":"2026-07-05T08:46:06.077504+00:00"}