{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YXHPJ6LINTE4Q65AWNA4BI5JNE","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":"0f6ab4fd47763af6c26348a738208759f8013ec02e8993f821c9be7946771250","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T14:43:17Z","title_canon_sha256":"9f1cb845f2b8c44b3019121b506414bec20618ddaa1dab96cf77fc72e58c223c"},"schema_version":"1.0","source":{"id":"2403.04547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04547","created_at":"2026-07-05T07:53:24Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04547v1","created_at":"2026-07-05T07:53:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04547","created_at":"2026-07-05T07:53:24Z"},{"alias_kind":"pith_short_12","alias_value":"YXHPJ6LINTE4","created_at":"2026-07-05T07:53:24Z"},{"alias_kind":"pith_short_16","alias_value":"YXHPJ6LINTE4Q65A","created_at":"2026-07-05T07:53:24Z"},{"alias_kind":"pith_short_8","alias_value":"YXHPJ6LI","created_at":"2026-07-05T07:53:24Z"}],"graph_snapshots":[{"event_id":"sha256:28ecae52c9577ba9297fb15a3d565491120aabed02be85e20851234bbefb682d","target":"graph","created_at":"2026-07-05T07:53:24Z","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/2403.04547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the effectiveness of data-balancing for mitigating biases in contrastive language-image pretraining (CLIP), identifying areas of strength and limitation. First, we reaffirm prior conclusions that CLIP models can inadvertently absorb societal stereotypes. To counter this, we present a novel algorithm, called Multi-Modal Moment Matching (M4), designed to reduce both representation and association biases (i.e. in first- and second-order statistics) in multimodal data. We use M4 to conduct an in-depth analysis taking into account various factors, such as the model, representation, and dat","authors_text":"Alexander D'Amour, Andreas Steiner, Ibrahim Alabdulmohsin, Priya Goyal, Xiaohua Zhai, Xiao Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T14:43:17Z","title":"CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04547","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:e0eb98e6f19024283076e13f8e19dfea4eb1989f92ce92778b82db8a26a0d54a","target":"record","created_at":"2026-07-05T07:53:24Z","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":"0f6ab4fd47763af6c26348a738208759f8013ec02e8993f821c9be7946771250","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T14:43:17Z","title_canon_sha256":"9f1cb845f2b8c44b3019121b506414bec20618ddaa1dab96cf77fc72e58c223c"},"schema_version":"1.0","source":{"id":"2403.04547","kind":"arxiv","version":1}},"canonical_sha256":"c5cef4f9686cc9c87ba0b341c0a3a969188ec95a3ed586ad29e85ce12406a218","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5cef4f9686cc9c87ba0b341c0a3a969188ec95a3ed586ad29e85ce12406a218","first_computed_at":"2026-07-05T07:53:24.876030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:24.876030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2xYN8ArcSnHqrCzblMTeSdRhbjrkw445FTqgaqiww+R350d0uxTcMvPesHTtrD7AuYzTvhZECN/c4eQBJCMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:24.876467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0eb98e6f19024283076e13f8e19dfea4eb1989f92ce92778b82db8a26a0d54a","sha256:28ecae52c9577ba9297fb15a3d565491120aabed02be85e20851234bbefb682d"],"state_sha256":"51e56978e49cadea1aeb42b0188240ad6c012d5571f1d1ed83e6234fc22da0c0"}