{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:26MRUWEVT2QC5SSFLYT5X7GHZS","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":"f7f471c8ebcd00451a7716c63fdc4d67e4435d0cfa731c85df33f0d12b18773c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T17:54:50Z","title_canon_sha256":"2e3665e18bd97421bcf0f24d2bf3928672c9a258bec06311c82a62a685e30a49"},"schema_version":"1.0","source":{"id":"2203.11926","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.11926","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.11926v3","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11926","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"26MRUWEVT2QC","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"26MRUWEVT2QC5SSF","created_at":"2026-07-05T05:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"26MRUWEV","created_at":"2026-07-05T05:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:60f8e9ad66a16f0f329c2e5ebf5076ac466a1dcc7b5769e03842adb7c9277486","target":"graph","created_at":"2026-07-05T05:13:32Z","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/2203.11926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose focal modulation networks (FocalNets in short), where self-attention (SA) is completely replaced by a focal modulation mechanism for modeling token interactions in vision. Focal modulation comprises three components: (i) hierarchical contextualization, implemented using a stack of depth-wise convolutional layers, to encode visual contexts from short to long ranges, (ii) gated aggregation to selectively gather contexts for each query token based on its\n  content, and (iii) element-wise modulation or affine transformation to inject the aggregated context into the query. Extensive expe","authors_text":"Chunyuan Li, Jianfeng Gao, Jianwei Yang, Lu Yuan, Xiyang Dai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T17:54:50Z","title":"Focal Modulation Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11926","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":"sha256:0bdea1ff32ea7da1dfe3d2f1bf88f960af8a3d4fbf11ea731a844f96b8dfe595","target":"record","created_at":"2026-07-05T05:13:32Z","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":"f7f471c8ebcd00451a7716c63fdc4d67e4435d0cfa731c85df33f0d12b18773c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-22T17:54:50Z","title_canon_sha256":"2e3665e18bd97421bcf0f24d2bf3928672c9a258bec06311c82a62a685e30a49"},"schema_version":"1.0","source":{"id":"2203.11926","kind":"arxiv","version":3}},"canonical_sha256":"d7991a58959ea02eca455e27dbfcc7cca625904591cd93d8b858025db7e9ea78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7991a58959ea02eca455e27dbfcc7cca625904591cd93d8b858025db7e9ea78","first_computed_at":"2026-07-05T05:13:32.898046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:32.898046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AMNwHFoG3uWAw2Gp4l9Csx3IkYJx+wdh7JXVkfeM0RT1OE6yGs0vXcVKhffeZb7Edm2mdFItdeMZd8LZpowvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:32.898481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.11926","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bdea1ff32ea7da1dfe3d2f1bf88f960af8a3d4fbf11ea731a844f96b8dfe595","sha256:60f8e9ad66a16f0f329c2e5ebf5076ac466a1dcc7b5769e03842adb7c9277486"],"state_sha256":"8a91c38839a1fd390cb790078405a1931473a2f2e675be9a3df9954565e3f033"}