{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QPTYJ23EBH5TKRHYWS2Y7KE3ZF","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":"a741ebc855013dafc468cbb289e2b77785f45231f32c8064917601fc94962d99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-30T22:44:12Z","title_canon_sha256":"c7970e5ff153bce232c2577c41e059ff53775d04b1bfee6ba7433b8ad444a8fe"},"schema_version":"1.0","source":{"id":"2107.00135","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.00135","created_at":"2026-07-05T05:21:22Z"},{"alias_kind":"arxiv_version","alias_value":"2107.00135v3","created_at":"2026-07-05T05:21:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.00135","created_at":"2026-07-05T05:21:22Z"},{"alias_kind":"pith_short_12","alias_value":"QPTYJ23EBH5T","created_at":"2026-07-05T05:21:22Z"},{"alias_kind":"pith_short_16","alias_value":"QPTYJ23EBH5TKRHY","created_at":"2026-07-05T05:21:22Z"},{"alias_kind":"pith_short_8","alias_value":"QPTYJ23E","created_at":"2026-07-05T05:21:22Z"}],"graph_snapshots":[{"event_id":"sha256:9172f52506f91576efacffdbf6a0955c43d05206ce6c9d754b25352b6b26e7c8","target":"graph","created_at":"2026-07-05T05:21:22Z","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/2107.00135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-atten","authors_text":"Anurag Arnab, Aren Jansen, Arsha Nagrani, Chen Sun, Cordelia Schmid, Shan Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-30T22:44:12Z","title":"Attention Bottlenecks for Multimodal Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.00135","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":"sha256:7eb1a95d309f3c2796a1b48e5256df53ce29ba45b6d6f93940e5a9a6743e4416","target":"record","created_at":"2026-07-05T05:21:22Z","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":"a741ebc855013dafc468cbb289e2b77785f45231f32c8064917601fc94962d99","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-30T22:44:12Z","title_canon_sha256":"c7970e5ff153bce232c2577c41e059ff53775d04b1bfee6ba7433b8ad444a8fe"},"schema_version":"1.0","source":{"id":"2107.00135","kind":"arxiv","version":3}},"canonical_sha256":"83e784eb6409fb3544f8b4b58fa89bc97d99a3fe2afd928d4d2d5e4b62feda4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83e784eb6409fb3544f8b4b58fa89bc97d99a3fe2afd928d4d2d5e4b62feda4c","first_computed_at":"2026-07-05T05:21:22.706880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:22.706880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JsJj0FborJbMyEOmksJqIThG2jybyO4y2tXALypqrv9yGXpqOAChSOCl0zGjN0Id58GJaHIyF9zlS/KkAJL+Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:22.707402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.00135","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7eb1a95d309f3c2796a1b48e5256df53ce29ba45b6d6f93940e5a9a6743e4416","sha256:9172f52506f91576efacffdbf6a0955c43d05206ce6c9d754b25352b6b26e7c8"],"state_sha256":"cecd1e953343b4def6ae1591243dc1cacdfd8256bac0f969062d7995813230ed"}