{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DENAQIKQASPHM7A7ATOK2IZZJA","short_pith_number":"pith:DENAQIKQ","schema_version":"1.0","canonical_sha256":"191a082150049e767c1f04dcad23394824aac446373084ad633c131631174e97","source":{"kind":"arxiv","id":"2211.08543","version":1},"attestation_state":"computed","paper":{"title":"Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhang, Junxiao Wang, Leijie Wu, Richard Yida Xu, Song Guo, Wenchao Xu, Yaohong Ding","submitted_at":"2022-11-13T15:18:31Z","abstract_excerpt":"Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent transformer designs from NLP to adapt vision tasks, while ignoring the fundamental difference between ``how MSA works in image and language settings''. Language naturally contains highly semantic structures that are directly interpretable by humans. Its basic unit (word) is discrete without redundant information, which readily supports interpretable studies"},"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":"2211.08543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-13T15:18:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3143162815f2fb898c590ee7149a66c4d7ec1f00dc7cff00cb750fd99ecd954e","abstract_canon_sha256":"210ffc65a063d4c94b9568c9d3b49c3839a1a0a5128432f3164d75d9823c6480"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:41.177574Z","signature_b64":"oUHsV7EC/8FclUnjNXywEG5iw2j1ZqLsTV0m9AldjupcI5toY512M2W6K4TR/ucFzt3QojGJ1b4H8KY4W6FuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"191a082150049e767c1f04dcad23394824aac446373084ad633c131631174e97","last_reissued_at":"2026-07-05T05:16:41.177210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:41.177210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jie Zhang, Junxiao Wang, Leijie Wu, Richard Yida Xu, Song Guo, Wenchao Xu, Yaohong Ding","submitted_at":"2022-11-13T15:18:31Z","abstract_excerpt":"Self-attention mechanisms, especially multi-head self-attention (MSA), have achieved great success in many fields such as computer vision and natural language processing. However, many existing vision transformer (ViT) works simply inherent transformer designs from NLP to adapt vision tasks, while ignoring the fundamental difference between ``how MSA works in image and language settings''. Language naturally contains highly semantic structures that are directly interpretable by humans. Its basic unit (word) is discrete without redundant information, which readily supports interpretable studies"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08543","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/2211.08543/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":"2211.08543","created_at":"2026-07-05T05:16:41.177265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08543v1","created_at":"2026-07-05T05:16:41.177265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08543","created_at":"2026-07-05T05:16:41.177265+00:00"},{"alias_kind":"pith_short_12","alias_value":"DENAQIKQASPH","created_at":"2026-07-05T05:16:41.177265+00:00"},{"alias_kind":"pith_short_16","alias_value":"DENAQIKQASPHM7A7","created_at":"2026-07-05T05:16:41.177265+00:00"},{"alias_kind":"pith_short_8","alias_value":"DENAQIKQ","created_at":"2026-07-05T05:16:41.177265+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/DENAQIKQASPHM7A7ATOK2IZZJA","json":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA.json","graph_json":"https://pith.science/api/pith-number/DENAQIKQASPHM7A7ATOK2IZZJA/graph.json","events_json":"https://pith.science/api/pith-number/DENAQIKQASPHM7A7ATOK2IZZJA/events.json","paper":"https://pith.science/paper/DENAQIKQ"},"agent_actions":{"view_html":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA","download_json":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA.json","view_paper":"https://pith.science/paper/DENAQIKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08543&json=true","fetch_graph":"https://pith.science/api/pith-number/DENAQIKQASPHM7A7ATOK2IZZJA/graph.json","fetch_events":"https://pith.science/api/pith-number/DENAQIKQASPHM7A7ATOK2IZZJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA/action/storage_attestation","attest_author":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA/action/author_attestation","sign_citation":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA/action/citation_signature","submit_replication":"https://pith.science/pith/DENAQIKQASPHM7A7ATOK2IZZJA/action/replication_record"}},"created_at":"2026-07-05T05:16:41.177265+00:00","updated_at":"2026-07-05T05:16:41.177265+00:00"}