{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O7GCJ6XULIYWDY74FJTYZZMIWS","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":"e79c6061f94310aaae63dde256eda2ca483c3e89a145fc2abebd61105d0806b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-23T06:21:53Z","title_canon_sha256":"e68e9501b38768fabdb921699f268a027e696c4c716087e25b62b5fc3792878b"},"schema_version":"1.0","source":{"id":"2203.12221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.12221","created_at":"2026-07-05T04:07:57Z"},{"alias_kind":"arxiv_version","alias_value":"2203.12221v1","created_at":"2026-07-05T04:07:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.12221","created_at":"2026-07-05T04:07:57Z"},{"alias_kind":"pith_short_12","alias_value":"O7GCJ6XULIYW","created_at":"2026-07-05T04:07:57Z"},{"alias_kind":"pith_short_16","alias_value":"O7GCJ6XULIYWDY74","created_at":"2026-07-05T04:07:57Z"},{"alias_kind":"pith_short_8","alias_value":"O7GCJ6XU","created_at":"2026-07-05T04:07:57Z"}],"graph_snapshots":[{"event_id":"sha256:a440d1d9b0069631c3a050afa9f92e44496a310ee0de54573ac2b7f12dc71445","target":"graph","created_at":"2026-07-05T04:07:57Z","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/2203.12221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable success of deep multi-modal learning in practice, it has not been well-explained in theory. Recently, it has been observed that the best uni-modal network outperforms the jointly trained multi-modal network, which is counter-intuitive since multiple signals generally bring more information. This work provides a theoretical explanation for the emergence of such performance gap in neural networks for the prevalent joint training framework. Based on a simplified data distribution that captures the realistic property of multi-modal data, we prove that for the multi-modal lat","authors_text":"Chang Zhou, Hongxia Yang, Junyang Lin, Longbo Huang, Yu Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-23T06:21:53Z","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.12221","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":"sha256:19016bb5a19ab1ddd0a638d7bc248a1a077a97b767a372078e4f082ba719ddf8","target":"record","created_at":"2026-07-05T04:07:57Z","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":"e79c6061f94310aaae63dde256eda2ca483c3e89a145fc2abebd61105d0806b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-23T06:21:53Z","title_canon_sha256":"e68e9501b38768fabdb921699f268a027e696c4c716087e25b62b5fc3792878b"},"schema_version":"1.0","source":{"id":"2203.12221","kind":"arxiv","version":1}},"canonical_sha256":"77cc24faf45a3161e3fc2a678ce588b499d3d0d0fe199ae6209e67dfd49cbb8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77cc24faf45a3161e3fc2a678ce588b499d3d0d0fe199ae6209e67dfd49cbb8a","first_computed_at":"2026-07-05T04:07:57.067595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:57.067595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X20dgwffH8HHvOpMM3y1zwT4fP64Tfa2jA6GtOvwZVCwVFF/EltfGUDpkDK4ozbxYAn4ur0cLntGB6iqwERpCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:57.068016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.12221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19016bb5a19ab1ddd0a638d7bc248a1a077a97b767a372078e4f082ba719ddf8","sha256:a440d1d9b0069631c3a050afa9f92e44496a310ee0de54573ac2b7f12dc71445"],"state_sha256":"0731ec70c49c91d2f6368e6a2e45f7d3c0133a666684ed64df97f9ae507e4e84"}