{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QOMJKHT36QOZRWCCGVRW5B7DXL","short_pith_number":"pith:QOMJKHT3","canonical_record":{"source":{"id":"2507.10203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T12:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"940f2289dfa4b569823c523e50ce162a60b911dccdf544d4b61c9d7f628a4e32","abstract_canon_sha256":"467d29bd17664599ed4aa409aa689308c671814756bc1272ffcdc95fbf205c09"},"schema_version":"1.0"},"canonical_sha256":"8398951e7bf41d98d84235636e87e3bac0771c6742815c1456bd87c0dffd9ad7","source":{"kind":"arxiv","id":"2507.10203","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10203","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10203v2","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10203","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"QOMJKHT36QOZ","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"QOMJKHT36QOZRWCC","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"QOMJKHT3","created_at":"2026-07-05T11:40:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QOMJKHT36QOZRWCCGVRW5B7DXL","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T12:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"940f2289dfa4b569823c523e50ce162a60b911dccdf544d4b61c9d7f628a4e32","abstract_canon_sha256":"467d29bd17664599ed4aa409aa689308c671814756bc1272ffcdc95fbf205c09"},"schema_version":"1.0"},"canonical_sha256":"8398951e7bf41d98d84235636e87e3bac0771c6742815c1456bd87c0dffd9ad7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:01.162493Z","signature_b64":"tne5RtN3yNOivudBYUGrkOatqVaidE7s3AloryDdoz+VsWe+fLNM5cLU7fxcy6ReonjBjHjv0G3L2gvYgTZyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8398951e7bf41d98d84235636e87e3bac0771c6742815c1456bd87c0dffd9ad7","last_reissued_at":"2026-07-05T11:40:01.161994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:01.161994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10203","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGI6yL60WK9ADS49SIopeb6qyX9M+b/5Lc7iR7ajsyONlHiILFw5WWMyi6C3V4jvaIlCBnuB74SfE1XcELmNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:55:21.264759Z"},"content_sha256":"095671ace0ecb0aceef7a4089352bb7182fa83645a7f1094cc401a0d6c91fb29","schema_version":"1.0","event_id":"sha256:095671ace0ecb0aceef7a4089352bb7182fa83645a7f1094cc401a0d6c91fb29"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QOMJKHT36QOZRWCCGVRW5B7DXL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Multimodal Learning via Imbalanced Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunbo Luo, Shicai Wei, Yang Luo","submitted_at":"2025-07-14T12:14:57Z","abstract_excerpt":"Multimodal learning often encounters the under-optimized problem and may perform worse than unimodal learning. Existing approaches attribute this issue to imbalanced learning across modalities and tend to address it through gradient balancing. However, this paper argues that balanced learning is not the optimal setting for multimodal learning. With bias-variance analysis, we prove that imbalanced dependency on each modality obeying the inverse ratio of their variances contributes to optimal performance. To this end, we propose the Asymmetric Representation Learning(ARL) strategy to assist mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10203","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/2507.10203/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":"2026-07-05T11:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+AbTMJfNkA/WktY6Cf9zKDxDnNHdq7H6t3IgRRfsWL8cpGe1HOICz0wUKIQvr4McPyCNWDVnESgWpbEll/kKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:55:21.265139Z"},"content_sha256":"c3f33b7be4b51473fddc43d43fed62e15da3c701d4c97b619428889d7d61819e","schema_version":"1.0","event_id":"sha256:c3f33b7be4b51473fddc43d43fed62e15da3c701d4c97b619428889d7d61819e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QOMJKHT36QOZRWCCGVRW5B7DXL/bundle.json","state_url":"https://pith.science/pith/QOMJKHT36QOZRWCCGVRW5B7DXL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QOMJKHT36QOZRWCCGVRW5B7DXL/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":"2026-08-07T10:55:21Z","links":{"resolver":"https://pith.science/pith/QOMJKHT36QOZRWCCGVRW5B7DXL","bundle":"https://pith.science/pith/QOMJKHT36QOZRWCCGVRW5B7DXL/bundle.json","state":"https://pith.science/pith/QOMJKHT36QOZRWCCGVRW5B7DXL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QOMJKHT36QOZRWCCGVRW5B7DXL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QOMJKHT36QOZRWCCGVRW5B7DXL","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":"467d29bd17664599ed4aa409aa689308c671814756bc1272ffcdc95fbf205c09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T12:14:57Z","title_canon_sha256":"940f2289dfa4b569823c523e50ce162a60b911dccdf544d4b61c9d7f628a4e32"},"schema_version":"1.0","source":{"id":"2507.10203","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10203","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10203v2","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10203","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"QOMJKHT36QOZ","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_16","alias_value":"QOMJKHT36QOZRWCC","created_at":"2026-07-05T11:40:01Z"},{"alias_kind":"pith_short_8","alias_value":"QOMJKHT3","created_at":"2026-07-05T11:40:01Z"}],"graph_snapshots":[{"event_id":"sha256:c3f33b7be4b51473fddc43d43fed62e15da3c701d4c97b619428889d7d61819e","target":"graph","created_at":"2026-07-05T11:40:01Z","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/2507.10203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal learning often encounters the under-optimized problem and may perform worse than unimodal learning. Existing approaches attribute this issue to imbalanced learning across modalities and tend to address it through gradient balancing. However, this paper argues that balanced learning is not the optimal setting for multimodal learning. With bias-variance analysis, we prove that imbalanced dependency on each modality obeying the inverse ratio of their variances contributes to optimal performance. To this end, we propose the Asymmetric Representation Learning(ARL) strategy to assist mult","authors_text":"Chunbo Luo, Shicai Wei, Yang Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T12:14:57Z","title":"Improving Multimodal Learning via Imbalanced Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10203","kind":"arxiv","version":2},"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":"sha256:095671ace0ecb0aceef7a4089352bb7182fa83645a7f1094cc401a0d6c91fb29","target":"record","created_at":"2026-07-05T11:40:01Z","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":"467d29bd17664599ed4aa409aa689308c671814756bc1272ffcdc95fbf205c09","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T12:14:57Z","title_canon_sha256":"940f2289dfa4b569823c523e50ce162a60b911dccdf544d4b61c9d7f628a4e32"},"schema_version":"1.0","source":{"id":"2507.10203","kind":"arxiv","version":2}},"canonical_sha256":"8398951e7bf41d98d84235636e87e3bac0771c6742815c1456bd87c0dffd9ad7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8398951e7bf41d98d84235636e87e3bac0771c6742815c1456bd87c0dffd9ad7","first_computed_at":"2026-07-05T11:40:01.161994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:01.161994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tne5RtN3yNOivudBYUGrkOatqVaidE7s3AloryDdoz+VsWe+fLNM5cLU7fxcy6ReonjBjHjv0G3L2gvYgTZyCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:01.162493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10203","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:095671ace0ecb0aceef7a4089352bb7182fa83645a7f1094cc401a0d6c91fb29","sha256:c3f33b7be4b51473fddc43d43fed62e15da3c701d4c97b619428889d7d61819e"],"state_sha256":"577d086a3d0b47126cb6345ccc42f54918906b565884d7279e0d85bf8e5da5af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2xHIHx75ulB5Ajr0TRWzDkqzdkWWW/6UCWSx9nlbfKZXrnLH7SLcAhl/VGb7ij+dzgsOUktxtS9A3WdDuinBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:55:21.267984Z","bundle_sha256":"4c7c4150dd3db1451bd11253df0025782b725220803ffeeeb10689e6d13aad2a"}}