{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VZ6BU4LEAXT3IFZ35AGILH7JGQ","short_pith_number":"pith:VZ6BU4LE","schema_version":"1.0","canonical_sha256":"ae7c1a716405e7b4173be80c859fe934059f931330ee25a1be2e942b1c6d2817","source":{"kind":"arxiv","id":"2203.05922","version":1},"attestation_state":"computed","paper":{"title":"Visualizing and Understanding Patch Interactions in Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Jie Ma, Tao Mei, Ting Yao, Wei Zhang, Yalong Bai","submitted_at":"2022-03-11T13:48:11Z","abstract_excerpt":"Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having good success, the literature seldom explores the explainability of vision transformer, and there is no clear picture of how the attention mechanism with respect to the correlation across comprehensive patches will impact the performance and what is the further potential. In this work, we propose a novel explainable visualization approach to analyze and interpre"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.05922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-11T13:48:11Z","cross_cats_sorted":[],"title_canon_sha256":"76612d5ddb7a312f340ac8b291d8927c4ef2033c7367f39afeaffa6555407faf","abstract_canon_sha256":"0a9ae40826477c14a81f919a23da4da8f996ce3046320e58e316f79183bba623"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:10.919062Z","signature_b64":"s5Pns1bif4QdZQYt7+ikTjPvBp71WZRtCnxkiwSWsBLMfQTnAwOHSuuN/s1ZrLqbkxkMj8SmwvrJ1dbi7FPFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae7c1a716405e7b4173be80c859fe934059f931330ee25a1be2e942b1c6d2817","last_reissued_at":"2026-07-05T04:04:10.918724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:10.918724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visualizing and Understanding Patch Interactions in Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Jie Ma, Tao Mei, Ting Yao, Wei Zhang, Yalong Bai","submitted_at":"2022-03-11T13:48:11Z","abstract_excerpt":"Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having good success, the literature seldom explores the explainability of vision transformer, and there is no clear picture of how the attention mechanism with respect to the correlation across comprehensive patches will impact the performance and what is the further potential. In this work, we propose a novel explainable visualization approach to analyze and interpre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05922","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.05922/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.05922","created_at":"2026-07-05T04:04:10.918781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05922v1","created_at":"2026-07-05T04:04:10.918781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05922","created_at":"2026-07-05T04:04:10.918781+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZ6BU4LEAXT3","created_at":"2026-07-05T04:04:10.918781+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZ6BU4LEAXT3IFZ3","created_at":"2026-07-05T04:04:10.918781+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZ6BU4LE","created_at":"2026-07-05T04:04:10.918781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ","json":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ.json","graph_json":"https://pith.science/api/pith-number/VZ6BU4LEAXT3IFZ35AGILH7JGQ/graph.json","events_json":"https://pith.science/api/pith-number/VZ6BU4LEAXT3IFZ35AGILH7JGQ/events.json","paper":"https://pith.science/paper/VZ6BU4LE"},"agent_actions":{"view_html":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ","download_json":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ.json","view_paper":"https://pith.science/paper/VZ6BU4LE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05922&json=true","fetch_graph":"https://pith.science/api/pith-number/VZ6BU4LEAXT3IFZ35AGILH7JGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/VZ6BU4LEAXT3IFZ35AGILH7JGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ/action/storage_attestation","attest_author":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ/action/author_attestation","sign_citation":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ/action/citation_signature","submit_replication":"https://pith.science/pith/VZ6BU4LEAXT3IFZ35AGILH7JGQ/action/replication_record"}},"created_at":"2026-07-05T04:04:10.918781+00:00","updated_at":"2026-07-05T04:04:10.918781+00:00"}