{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z2VNHXRF7UVLN4DQ4IDPN7SUQ2","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":"3e14a0c0625eead350bd3a3d2f23e1ee4c2aa02c971e47524062048abc33c5e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-23T17:51:39Z","title_canon_sha256":"aa0bc380c99072a7d9ae3ed286c4c51972925759cf3fbf24ecd9c0c954e86dc3"},"schema_version":"1.0","source":{"id":"2301.09595","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09595","created_at":"2026-07-05T05:44:39Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09595v2","created_at":"2026-07-05T05:44:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09595","created_at":"2026-07-05T05:44:39Z"},{"alias_kind":"pith_short_12","alias_value":"Z2VNHXRF7UVL","created_at":"2026-07-05T05:44:39Z"},{"alias_kind":"pith_short_16","alias_value":"Z2VNHXRF7UVLN4DQ","created_at":"2026-07-05T05:44:39Z"},{"alias_kind":"pith_short_8","alias_value":"Z2VNHXRF","created_at":"2026-07-05T05:44:39Z"}],"graph_snapshots":[{"event_id":"sha256:43987f09673a738064e5de5890b0808c24e03be5c7e0dec8e9e92983edfc2094","target":"graph","created_at":"2026-07-05T05:44:39Z","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/2301.09595/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring very little fusion engineering. The resulting representations are however fully entangled throughout the network, which may not always be desirable: in learning, contrastive audio-visual self-supervised learning requires independent audio and visual features to operate, otherwise learning collapses; in inference, evaluation of audio-visual models should be possible on benchmarks having just audio or just video. In this ","authors_text":"Adri\\`a Recasens, Andrew Zisserman, Antoine Miech, Drew Jaegle, Jason Lin, Jean-Baptiste Alayrac, Jo\\=ao Carreira, Lucas Smaira, Luyu Wang, Pauline Luc, Ross Hemsley","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-23T17:51:39Z","title":"Zorro: the masked multimodal transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09595","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":"sha256:607135669fa6a84bafd29a04ce0e856b23466653a6abcbf44da292fd4e0f2cf6","target":"record","created_at":"2026-07-05T05:44:39Z","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":"3e14a0c0625eead350bd3a3d2f23e1ee4c2aa02c971e47524062048abc33c5e3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-23T17:51:39Z","title_canon_sha256":"aa0bc380c99072a7d9ae3ed286c4c51972925759cf3fbf24ecd9c0c954e86dc3"},"schema_version":"1.0","source":{"id":"2301.09595","kind":"arxiv","version":2}},"canonical_sha256":"ceaad3de25fd2ab6f070e206f6fe5486aa24cf8e55d7f8f54d2a63727ee650f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceaad3de25fd2ab6f070e206f6fe5486aa24cf8e55d7f8f54d2a63727ee650f2","first_computed_at":"2026-07-05T05:44:39.913969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:39.913969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i9xfjldMDqpubPTCfHgZYc+mXWSrsA1kmuG2iXg+EeWuNjIhFAfLduJxpKi794MUyvPphhJYD+zVt66EdSh0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:39.914400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09595","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:607135669fa6a84bafd29a04ce0e856b23466653a6abcbf44da292fd4e0f2cf6","sha256:43987f09673a738064e5de5890b0808c24e03be5c7e0dec8e9e92983edfc2094"],"state_sha256":"d4ea7763bd940d10aa72168a03b5d1fbbdc27e2d4445ddc502adbccf6ea9257b"}