{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KVWEU6I4HYS4MX74JSNBYIDSDA","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":"faa921639ebe4d988ea46bd43b1f129a52aa025f7b688bd39113c365983abd7b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T21:41:06Z","title_canon_sha256":"1439523760a52a8e8a8881024e6df9804470e2816248a26a135d194ce57f5d34"},"schema_version":"1.0","source":{"id":"2212.08158","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08158","created_at":"2026-07-05T09:08:44Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08158v3","created_at":"2026-07-05T09:08:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08158","created_at":"2026-07-05T09:08:44Z"},{"alias_kind":"pith_short_12","alias_value":"KVWEU6I4HYS4","created_at":"2026-07-05T09:08:44Z"},{"alias_kind":"pith_short_16","alias_value":"KVWEU6I4HYS4MX74","created_at":"2026-07-05T09:08:44Z"},{"alias_kind":"pith_short_8","alias_value":"KVWEU6I4","created_at":"2026-07-05T09:08:44Z"}],"graph_snapshots":[{"event_id":"sha256:cd8267ed4a038b8142f24eca51ec23ebcdeacfb0d211faba75b88d0db07cde3f","target":"graph","created_at":"2026-07-05T09:08:44Z","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/2212.08158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision and language models (VL) are known to exploit unrobust indicators in individual modalities (e.g., introduced by distributional biases) instead of focusing on relevant information in each modality. That a unimodal model achieves similar accuracy on a VL task to a multimodal one, indicates that so-called unimodal collapse occurred. However, accuracy-based tests fail to detect e.g., when the model prediction is wrong, while the model used relevant information from a modality. Instead, we propose MM-SHAP, a performance-agnostic multimodality score based on Shapley values that reliably quant","authors_text":"Anette Frank, Letitia Parcalabescu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T21:41:06Z","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08158","kind":"arxiv","version":3},"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:e363d378128c0a9fa4d940e4b4e3f74eadf54d37e64e94b885af7dc2fa0978cc","target":"record","created_at":"2026-07-05T09:08:44Z","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":"faa921639ebe4d988ea46bd43b1f129a52aa025f7b688bd39113c365983abd7b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-15T21:41:06Z","title_canon_sha256":"1439523760a52a8e8a8881024e6df9804470e2816248a26a135d194ce57f5d34"},"schema_version":"1.0","source":{"id":"2212.08158","kind":"arxiv","version":3}},"canonical_sha256":"556c4a791c3e25c65ffc4c9a1c2072180cd5fca60a8ea58f4b04c9ac64685c9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"556c4a791c3e25c65ffc4c9a1c2072180cd5fca60a8ea58f4b04c9ac64685c9a","first_computed_at":"2026-07-05T09:08:44.760720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:44.760720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E4ObbdefV25qSCukiDFHADIeTESwZBKnssYNJ2eL8i0xR/GG5djINLd2LEhiQzJVoUIHB10B3+1ecJijuP20Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:44.761251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08158","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e363d378128c0a9fa4d940e4b4e3f74eadf54d37e64e94b885af7dc2fa0978cc","sha256:cd8267ed4a038b8142f24eca51ec23ebcdeacfb0d211faba75b88d0db07cde3f"],"state_sha256":"dd0bbdfa07a456c0d1c88fd1daaa9bd0f930cceaa530791daec503d21942504c"}