{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7CAG5NDWUBERZF5YUBVOGSXQS4","short_pith_number":"pith:7CAG5NDW","schema_version":"1.0","canonical_sha256":"f8806eb476a0491c97b8a06ae34af0973a3d41be873b0f627a82c7dffdcc7bcf","source":{"kind":"arxiv","id":"2308.06548","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Vision Transformer from the View of Path Ensemble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Wang, Hao Luo, Mike Zheng Shou, Pichao Wang, Shuning Chang","submitted_at":"2023-08-12T12:18:16Z","abstract_excerpt":"Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths. Specifically, we equivalently transform the traditional cascade of multi-head self-attention (MSA) and feed-forward network (FFN) into three parallel paths in each transformer layer. Then, we utilize the identity connection in our new transformer form and further transform the ViT into an explicit multi-path ensemble network. From the new perspective, these p"},"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":"2308.06548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-12T12:18:16Z","cross_cats_sorted":[],"title_canon_sha256":"173f0da47d99b793c03c0d3765e501e37e491e7c0bba8569d56774f9f73f57de","abstract_canon_sha256":"351a6a152bd6e4d1bb9d8ee408357be01f1e0c14d12fb7a30e96a8153365218d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:41.842239Z","signature_b64":"LO21am3+emVkNyG4VpaOP83tedGIAQpSXDHpKIQvjaebdUUjtTHNeBXUWKfKoph6wQ8yIetxT6v+8f7ng/cjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8806eb476a0491c97b8a06ae34af0973a3d41be873b0f627a82c7dffdcc7bcf","last_reissued_at":"2026-07-05T06:40:41.841819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:41.841819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Vision Transformer from the View of Path Ensemble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fan Wang, Hao Luo, Mike Zheng Shou, Pichao Wang, Shuning Chang","submitted_at":"2023-08-12T12:18:16Z","abstract_excerpt":"Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths. Specifically, we equivalently transform the traditional cascade of multi-head self-attention (MSA) and feed-forward network (FFN) into three parallel paths in each transformer layer. Then, we utilize the identity connection in our new transformer form and further transform the ViT into an explicit multi-path ensemble network. From the new perspective, these p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06548","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/2308.06548/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":"2308.06548","created_at":"2026-07-05T06:40:41.841868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.06548v1","created_at":"2026-07-05T06:40:41.841868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06548","created_at":"2026-07-05T06:40:41.841868+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CAG5NDWUBER","created_at":"2026-07-05T06:40:41.841868+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CAG5NDWUBERZF5Y","created_at":"2026-07-05T06:40:41.841868+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CAG5NDW","created_at":"2026-07-05T06:40:41.841868+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/7CAG5NDWUBERZF5YUBVOGSXQS4","json":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4.json","graph_json":"https://pith.science/api/pith-number/7CAG5NDWUBERZF5YUBVOGSXQS4/graph.json","events_json":"https://pith.science/api/pith-number/7CAG5NDWUBERZF5YUBVOGSXQS4/events.json","paper":"https://pith.science/paper/7CAG5NDW"},"agent_actions":{"view_html":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4","download_json":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4.json","view_paper":"https://pith.science/paper/7CAG5NDW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.06548&json=true","fetch_graph":"https://pith.science/api/pith-number/7CAG5NDWUBERZF5YUBVOGSXQS4/graph.json","fetch_events":"https://pith.science/api/pith-number/7CAG5NDWUBERZF5YUBVOGSXQS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4/action/storage_attestation","attest_author":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4/action/author_attestation","sign_citation":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4/action/citation_signature","submit_replication":"https://pith.science/pith/7CAG5NDWUBERZF5YUBVOGSXQS4/action/replication_record"}},"created_at":"2026-07-05T06:40:41.841868+00:00","updated_at":"2026-07-05T06:40:41.841868+00:00"}