{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ALDQSNIMU2JZHE2AAU2KVJWSKD","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":"6e6c2c5ec56d7bd054cb38980280f487673c68d9cfaa9d9cac921b19336ca9f2","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-12T15:22:27Z","title_canon_sha256":"c1c729f0e083055fb43c04131629d94d7ee644c1a4681baa2cc658006b22378d"},"schema_version":"1.0","source":{"id":"2603.12046","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.12046","created_at":"2026-06-09T01:05:15Z"},{"alias_kind":"arxiv_version","alias_value":"2603.12046v2","created_at":"2026-06-09T01:05:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12046","created_at":"2026-06-09T01:05:15Z"},{"alias_kind":"pith_short_12","alias_value":"ALDQSNIMU2JZ","created_at":"2026-06-09T01:05:15Z"},{"alias_kind":"pith_short_16","alias_value":"ALDQSNIMU2JZHE2A","created_at":"2026-06-09T01:05:15Z"},{"alias_kind":"pith_short_8","alias_value":"ALDQSNIM","created_at":"2026-06-09T01:05:15Z"}],"graph_snapshots":[{"event_id":"sha256:ea5bc47de5c105416335e3cabf25b2daceb2692f2914157962627fc0e8a5238b","target":"graph","created_at":"2026-06-09T01:05:15Z","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/2603.12046/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Speech Recognition (AVSR) leverages both acoustic and visual information for robust recognition under noise. However, how models balance these modalities remains unclear. We present Dr. SHAP-AV, a framework using Shapley values to analyze modality contributions in AVSR. Through experiments on six models across two benchmarks and varying SNR levels, we introduce three analyses: Global SHAP for overall modality balance, Generative SHAP for contribution dynamics during decoding, and Temporal Alignment SHAP for input-output correspondence. Our findings reveal that models shift toward ","authors_text":"Maja Pantic, Stavros Petridis, Umberto Cappellazzo","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-12T15:22:27Z","title":"Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.12046","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:b15dda2cb3c1418d17c96b4e32c376f522cd1fb28c0bd6f2c9b1a88a99ee3572","target":"record","created_at":"2026-06-09T01:05:15Z","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":"6e6c2c5ec56d7bd054cb38980280f487673c68d9cfaa9d9cac921b19336ca9f2","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-12T15:22:27Z","title_canon_sha256":"c1c729f0e083055fb43c04131629d94d7ee644c1a4681baa2cc658006b22378d"},"schema_version":"1.0","source":{"id":"2603.12046","kind":"arxiv","version":2}},"canonical_sha256":"02c709350ca6939393400534aaa6d250e495c0b4025a0c34d80c1c40e3a0b57d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02c709350ca6939393400534aaa6d250e495c0b4025a0c34d80c1c40e3a0b57d","first_computed_at":"2026-06-09T01:05:15.870908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:15.870908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8i6MLYlXMLzUDOo6tRlUP9lAVbCpugVnSRdPkwGckZZRE5ixf+BAmaLS5UI7zOSyr8SPEakYrQLfvhsCicBvBQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:15.871470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.12046","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b15dda2cb3c1418d17c96b4e32c376f522cd1fb28c0bd6f2c9b1a88a99ee3572","sha256:ea5bc47de5c105416335e3cabf25b2daceb2692f2914157962627fc0e8a5238b"],"state_sha256":"1fcf73149072af7727fd65cf24a358f2ef5603f9f7dae1ecd2797097a6f7d951"}