{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FEF2XJZEVU743EA5UIAYA3JM52","short_pith_number":"pith:FEF2XJZE","canonical_record":{"source":{"id":"2407.19394","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T04:23:40Z","cross_cats_sorted":[],"title_canon_sha256":"72148ea1085bf6a5da03f0b4f655bafe04c904ff871b3d9e686d240a403b7bd9","abstract_canon_sha256":"4dbe6b09f20aea7fa239f558670166bf6677a465aca02687475503028e58f2d9"},"schema_version":"1.0"},"canonical_sha256":"290baba724ad3fcd901da201806d2cee98dc14f46ecf648a3a64d20b516e8e37","source":{"kind":"arxiv","id":"2407.19394","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19394","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19394v4","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19394","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"FEF2XJZEVU74","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"FEF2XJZEVU743EA5","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"FEF2XJZE","created_at":"2026-07-05T10:01:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FEF2XJZEVU743EA5UIAYA3JM52","target":"record","payload":{"canonical_record":{"source":{"id":"2407.19394","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T04:23:40Z","cross_cats_sorted":[],"title_canon_sha256":"72148ea1085bf6a5da03f0b4f655bafe04c904ff871b3d9e686d240a403b7bd9","abstract_canon_sha256":"4dbe6b09f20aea7fa239f558670166bf6677a465aca02687475503028e58f2d9"},"schema_version":"1.0"},"canonical_sha256":"290baba724ad3fcd901da201806d2cee98dc14f46ecf648a3a64d20b516e8e37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:34.889217Z","signature_b64":"FNeYBbeM33TJeJJ73im6P9UC3PzI8TQppOMBHPgKZDnht+rZVQcxjV8rfotoQH4lbaKPg3WdOcRQA2YcAkUeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290baba724ad3fcd901da201806d2cee98dc14f46ecf648a3a64d20b516e8e37","last_reissued_at":"2026-07-05T10:01:34.888779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:34.888779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.19394","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbAfnvuOVCb9uanVY6L9dHS3gKm6oyTt74nFdSdJgr/dLg1rlzdR2mZeKK7czg3dqFcOjt2RrBn54Zft/q++Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:32:49.226419Z"},"content_sha256":"c4d0977749008380975297e25c70691716d508e0d201095085fabc6e4a1205ee","schema_version":"1.0","event_id":"sha256:c4d0977749008380975297e25c70691716d508e0d201095085fabc6e4a1205ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FEF2XJZEVU743EA5UIAYA3JM52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Luo, Guanghui Wang, Tianxiao Zhang, Wenju Xu","submitted_at":"2024-07-28T04:23:40Z","abstract_excerpt":"The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of ViT captures the global context from the outset, overlooking the inherent relationships between neighboring pixels in images or videos. Transformers mainly focus on global information while ignoring the fine-grained local details. Consequently, ViT lacks inductive bias during image or video dataset training. In contrast, convolutional neural networks (CNNs),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19394","kind":"arxiv","version":4},"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/2407.19394/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCcCT3mTmTxVw1NYkbKyGnBsc4S6rzsnz9kdunOY3yLKjDJbSvjIE1RxcDfthUKL0prVyO+VXjwzPvEQKbfCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:32:49.227017Z"},"content_sha256":"72f3db37762103d1ef08a2bfc286e2fe9b274d69af531be627b4355f9f6f4406","schema_version":"1.0","event_id":"sha256:72f3db37762103d1ef08a2bfc286e2fe9b274d69af531be627b4355f9f6f4406"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEF2XJZEVU743EA5UIAYA3JM52/bundle.json","state_url":"https://pith.science/pith/FEF2XJZEVU743EA5UIAYA3JM52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEF2XJZEVU743EA5UIAYA3JM52/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T08:32:49Z","links":{"resolver":"https://pith.science/pith/FEF2XJZEVU743EA5UIAYA3JM52","bundle":"https://pith.science/pith/FEF2XJZEVU743EA5UIAYA3JM52/bundle.json","state":"https://pith.science/pith/FEF2XJZEVU743EA5UIAYA3JM52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEF2XJZEVU743EA5UIAYA3JM52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FEF2XJZEVU743EA5UIAYA3JM52","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":"4dbe6b09f20aea7fa239f558670166bf6677a465aca02687475503028e58f2d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T04:23:40Z","title_canon_sha256":"72148ea1085bf6a5da03f0b4f655bafe04c904ff871b3d9e686d240a403b7bd9"},"schema_version":"1.0","source":{"id":"2407.19394","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19394","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19394v4","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19394","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"FEF2XJZEVU74","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"FEF2XJZEVU743EA5","created_at":"2026-07-05T10:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"FEF2XJZE","created_at":"2026-07-05T10:01:34Z"}],"graph_snapshots":[{"event_id":"sha256:72f3db37762103d1ef08a2bfc286e2fe9b274d69af531be627b4355f9f6f4406","target":"graph","created_at":"2026-07-05T10:01:34Z","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/2407.19394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Vision Transformer (ViT) leverages the Transformer's encoder to capture global information by dividing images into patches and achieves superior performance across various computer vision tasks. However, the self-attention mechanism of ViT captures the global context from the outset, overlooking the inherent relationships between neighboring pixels in images or videos. Transformers mainly focus on global information while ignoring the fine-grained local details. Consequently, ViT lacks inductive bias during image or video dataset training. In contrast, convolutional neural networks (CNNs),","authors_text":"Bo Luo, Guanghui Wang, Tianxiao Zhang, Wenju Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T04:23:40Z","title":"Depth-Wise Convolutions in Vision Transformers for Efficient Training on Small Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19394","kind":"arxiv","version":4},"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:c4d0977749008380975297e25c70691716d508e0d201095085fabc6e4a1205ee","target":"record","created_at":"2026-07-05T10:01:34Z","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":"4dbe6b09f20aea7fa239f558670166bf6677a465aca02687475503028e58f2d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-28T04:23:40Z","title_canon_sha256":"72148ea1085bf6a5da03f0b4f655bafe04c904ff871b3d9e686d240a403b7bd9"},"schema_version":"1.0","source":{"id":"2407.19394","kind":"arxiv","version":4}},"canonical_sha256":"290baba724ad3fcd901da201806d2cee98dc14f46ecf648a3a64d20b516e8e37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"290baba724ad3fcd901da201806d2cee98dc14f46ecf648a3a64d20b516e8e37","first_computed_at":"2026-07-05T10:01:34.888779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:34.888779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FNeYBbeM33TJeJJ73im6P9UC3PzI8TQppOMBHPgKZDnht+rZVQcxjV8rfotoQH4lbaKPg3WdOcRQA2YcAkUeDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:34.889217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19394","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4d0977749008380975297e25c70691716d508e0d201095085fabc6e4a1205ee","sha256:72f3db37762103d1ef08a2bfc286e2fe9b274d69af531be627b4355f9f6f4406"],"state_sha256":"64340c90a1d3f30025802a127cd61eb34d64cc9de6cd06ae3df8b80586a6702d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OJRbnZ7o/+61nIMwltS48dDmn1QMMPAHjkFxi2oxDXb9cj//XB1/YXNfg3SY5DTpmlT56vzeahlvhSxz1KaICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:32:49.231786Z","bundle_sha256":"fcd41fb10e3a3a1b6f82e2959414087b24614926384d826ea92a0a021a6a1e51"}}