{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QGN2M5FKAKNLRVCXIZL3SDNIHG","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":"c04736a5a359ce8a9810eaac3ca30a287a692b4eec89d28c96bf6cee5710ef8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T08:08:47Z","title_canon_sha256":"7c63f4434c1476bc87efb80da4942c43478f800e939063c58e16c8614eaf9a6c"},"schema_version":"1.0","source":{"id":"2111.15193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.15193","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"arxiv_version","alias_value":"2111.15193v2","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15193","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_12","alias_value":"QGN2M5FKAKNL","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_16","alias_value":"QGN2M5FKAKNLRVCX","created_at":"2026-07-05T04:14:26Z"},{"alias_kind":"pith_short_8","alias_value":"QGN2M5FK","created_at":"2026-07-05T04:14:26Z"}],"graph_snapshots":[{"event_id":"sha256:db00f7c7765d6bfc0ce25053deb32db843661955feffd7b9297dbd9484ea9c6b","target":"graph","created_at":"2026-07-05T04:14:26Z","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/2111.15193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models, however, usually designate the similar receptive fields of each token feature within each layer. Such a constraint inevitably limits the ability of each self-attention layer in capturing multi-scale features, thereby leading to performance degradation in handling images with multiple objects of different scales. To address this issue, we propose a novel and g","authors_text":"Daquan Zhou, Jiashi Feng, Shengfeng He, Sucheng Ren, Xinchao Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T08:08:47Z","title":"Shunted Self-Attention via Multi-Scale Token Aggregation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15193","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":"sha256:70a881dc2d17b4370caec864dcc54b9cfd579eb582f029397ac0fb2cd69b2831","target":"record","created_at":"2026-07-05T04:14:26Z","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":"c04736a5a359ce8a9810eaac3ca30a287a692b4eec89d28c96bf6cee5710ef8e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-30T08:08:47Z","title_canon_sha256":"7c63f4434c1476bc87efb80da4942c43478f800e939063c58e16c8614eaf9a6c"},"schema_version":"1.0","source":{"id":"2111.15193","kind":"arxiv","version":2}},"canonical_sha256":"819ba674aa029ab8d4574657b90da8399eec56c02e19166297b8e9d545d1b75d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"819ba674aa029ab8d4574657b90da8399eec56c02e19166297b8e9d545d1b75d","first_computed_at":"2026-07-05T04:14:26.527916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:14:26.527916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rrC+wZrGhjns7MXW4jjyyBXDlezEHVkK5OM3YD0N2+NuHxpA0G3BU7HhQHbu9UY3HX/M97vISNL7rxZCfQgWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:14:26.528268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.15193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70a881dc2d17b4370caec864dcc54b9cfd579eb582f029397ac0fb2cd69b2831","sha256:db00f7c7765d6bfc0ce25053deb32db843661955feffd7b9297dbd9484ea9c6b"],"state_sha256":"267102bfdbc707c192b2c95dceee09a0a6665aa9899d99d08b106a7f62c96cea"}