{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TT3RICPKYRS3FY4JXDC7E76GCC","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":"d478a83602944957b34370e53de2a8992cce62476ed58db061b463f9b876f76d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T20:15:03Z","title_canon_sha256":"11001cdb2ba338df635c6d5d3b948215b27f441fe9c6dd1eef8148a34150f8e1"},"schema_version":"1.0","source":{"id":"2112.05814","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05814","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05814v3","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05814","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"pith_short_12","alias_value":"TT3RICPKYRS3","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"pith_short_16","alias_value":"TT3RICPKYRS3FY4J","created_at":"2026-07-05T05:06:53Z"},{"alias_kind":"pith_short_8","alias_value":"TT3RICPK","created_at":"2026-07-05T05:06:53Z"}],"graph_snapshots":[{"event_id":"sha256:fbf518686fe94b0c172613b38b841437ceef747d190c56b84210cac53bb276ec","target":"graph","created_at":"2026-07-05T05:06:53Z","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/2112.05814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the use of deep features extracted from a pretrained Vision Transformer (ViT) as dense visual descriptors. We observe and empirically demonstrate that such features, when extractedfrom a self-supervised ViT model (DINO-ViT), exhibit several striking properties, including: (i) the features encode powerful, well-localized semantic information, at high spatial granularity, such as object parts; (ii) the encoded semantic information is shared across related, yet different object categories, and (iii) positional bias changes gradually throughout the layers. These properties allow us to des","authors_text":"Shai Bagon, Shir Amir, Tali Dekel, Yossi Gandelsman","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T20:15:03Z","title":"Deep ViT Features as Dense Visual Descriptors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05814","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":"sha256:06bfaae424148729fc0f337bb11857bc86415a256e6627812508c4baaee32f6d","target":"record","created_at":"2026-07-05T05:06:53Z","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":"d478a83602944957b34370e53de2a8992cce62476ed58db061b463f9b876f76d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T20:15:03Z","title_canon_sha256":"11001cdb2ba338df635c6d5d3b948215b27f441fe9c6dd1eef8148a34150f8e1"},"schema_version":"1.0","source":{"id":"2112.05814","kind":"arxiv","version":3}},"canonical_sha256":"9cf71409eac465b2e389b8c5f27fc610979ef8924945d7e16a9acd69394d601e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cf71409eac465b2e389b8c5f27fc610979ef8924945d7e16a9acd69394d601e","first_computed_at":"2026-07-05T05:06:53.681071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:53.681071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mFbLolQzTPcT9F69WviTOfo0JKGs7YVY+893Kh2TNUDanPMuZtWLH/OhAYTgE1mKWsKM4NXmfyD011b7jluLBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:53.681541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05814","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06bfaae424148729fc0f337bb11857bc86415a256e6627812508c4baaee32f6d","sha256:fbf518686fe94b0c172613b38b841437ceef747d190c56b84210cac53bb276ec"],"state_sha256":"cf72139d8445a20cdf5b623b49f1933f5831f43e72a7a4fafd7e5c5f6c6c77a3"}