{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DYBBKGEW2KZMUCMJWT4ZJXF523","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":"4acf88827af378c14009050c8b0556a30955d47aac3939c59738c8b217b2b1be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T13:33:11Z","title_canon_sha256":"e731e892947911db925a073cf08f17ba7d452f1b10d20b4b4049a376ce05b3f8"},"schema_version":"1.0","source":{"id":"2608.00076","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00076","created_at":"2026-08-04T00:32:13Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00076v1","created_at":"2026-08-04T00:32:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00076","created_at":"2026-08-04T00:32:13Z"},{"alias_kind":"pith_short_12","alias_value":"DYBBKGEW2KZM","created_at":"2026-08-04T00:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"DYBBKGEW2KZMUCMJ","created_at":"2026-08-04T00:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"DYBBKGEW","created_at":"2026-08-04T00:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:932c6e11ca728d030fe34226c3d70edb94473646d42fddb0988515914b27421a","target":"graph","created_at":"2026-08-04T00:32:13Z","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/2608.00076/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text. While existing explainability methods identify influential image regions or text tokens, they cannot answer a fundamental question: which modality drives a prediction? Consequently, a model may produce the correct output while relying on the wrong source of evidence, masking shortcut learning and unsafe reasoning. We formulate modality attribution as a complementary explainability objective for multimodal foundation models and propose Counterfac","authors_text":"Chao Wang, David Watson, Luis C. Garcia-Peraza-Herrera, Senka Krivic, Vahidin Hasic","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T13:33:11Z","title":"Which Modality Decides? Counterfactual Modality Attribution for Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00076","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:bb167af04d5abbac7cf05b39982c8bd08eb59c1cd6bde1ce7ca6bf7fbe7f30bb","target":"record","created_at":"2026-08-04T00:32:13Z","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":"4acf88827af378c14009050c8b0556a30955d47aac3939c59738c8b217b2b1be","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T13:33:11Z","title_canon_sha256":"e731e892947911db925a073cf08f17ba7d452f1b10d20b4b4049a376ce05b3f8"},"schema_version":"1.0","source":{"id":"2608.00076","kind":"arxiv","version":1}},"canonical_sha256":"1e02151896d2b2ca0989b4f994dcbdd6d9b77f1ef66b2e4637672af14f65c71c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e02151896d2b2ca0989b4f994dcbdd6d9b77f1ef66b2e4637672af14f65c71c","first_computed_at":"2026-08-04T00:32:13.910163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:32:13.910163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VCfRSk2YRKJg3E97OSmScAhPCTpU522iXgK2K1MQWJ4JhQy/Bl7yn7xbfcz0FDZuYBLr5hMNBE4gs+Kmd10aCg==","signature_status":"signed_v1","signed_at":"2026-08-04T00:32:13.911613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00076","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb167af04d5abbac7cf05b39982c8bd08eb59c1cd6bde1ce7ca6bf7fbe7f30bb","sha256:932c6e11ca728d030fe34226c3d70edb94473646d42fddb0988515914b27421a"],"state_sha256":"a6d045cdad80c5ae9a1492020e30ac550a5af2784783402a454e082c294c8cbc"}