{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:66HBBG2LPJABH3YVXPAZF2DLMO","short_pith_number":"pith:66HBBG2L","canonical_record":{"source":{"id":"2106.13112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T15:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"8e6beb1c41b1db3a49f86c45d0dd824451d461c7d2ab96710d52dffa1538a41b","abstract_canon_sha256":"9e00ce0fbb778b73583b201d394e0488be5cf233a9394e61d5122058b7b64e60"},"schema_version":"1.0"},"canonical_sha256":"f78e109b4b7a4013ef15bbc192e86b63b7bb2aa5145b3ed62a6664349719ab33","source":{"kind":"arxiv","id":"2106.13112","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13112","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13112v2","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13112","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"66HBBG2LPJAB","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"66HBBG2LPJABH3YV","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"66HBBG2L","created_at":"2026-07-05T02:52:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:66HBBG2LPJABH3YVXPAZF2DLMO","target":"record","payload":{"canonical_record":{"source":{"id":"2106.13112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T15:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"8e6beb1c41b1db3a49f86c45d0dd824451d461c7d2ab96710d52dffa1538a41b","abstract_canon_sha256":"9e00ce0fbb778b73583b201d394e0488be5cf233a9394e61d5122058b7b64e60"},"schema_version":"1.0"},"canonical_sha256":"f78e109b4b7a4013ef15bbc192e86b63b7bb2aa5145b3ed62a6664349719ab33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:46.249871Z","signature_b64":"G0Zh4szbtpfjUYvpHYRupijOdbBHjdwy0NDJ+XqIDs0r67zpeceC1sw86iXlcpqFh7SSCWMc3jBHgGzdVfjGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f78e109b4b7a4013ef15bbc192e86b63b7bb2aa5145b3ed62a6664349719ab33","last_reissued_at":"2026-07-05T02:52:46.249415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:46.249415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.13112","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXd4KyJCA4YLNomdxeelYg2BZCMRxsUcOKeGP0zgvPc1UCPbhfvakd2+S6cRtRk1rvg5EgOaAlH0XcrVVL5/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T22:04:33.684829Z"},"content_sha256":"f90690a26ed6ea034c587e413bc61ccc570113230db4caa45ec9f0a6685e5d45","schema_version":"1.0","event_id":"sha256:f90690a26ed6ea034c587e413bc61ccc570113230db4caa45ec9f0a6685e5d45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:66HBBG2LPJABH3YVXPAZF2DLMO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VOLO: Vision Outlooker for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiashi Feng, Li Yuan, Qibin Hou, Shuicheng Yan, Zihang Jiang","submitted_at":"2021-06-24T15:46:54Z","abstract_excerpt":"Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their performance is still inferior to that of the latest SOTA CNNs if no extra data are provided. In this work, we try to close the performance gap and demonstrate that attention-based models are indeed able to outperform CNNs. We find a major factor limiting the performance of ViTs for ImageNet classification is their low efficacy in encoding fine-level features "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13112","kind":"arxiv","version":2},"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/2106.13112/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":"2026-07-05T02:52:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWC041Im8nVv6Dr8P7Jq5YYGLrlEfX/hQZWlHi2PoO1JnmUQdrjmNJrBGGI79ZoIfoG/ZQd5bNs53CFc+Al8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T22:04:33.685200Z"},"content_sha256":"df1f80fb7bc2d242151277c83f1c66f4508208fb3f5bd15060dd53542b31dd8c","schema_version":"1.0","event_id":"sha256:df1f80fb7bc2d242151277c83f1c66f4508208fb3f5bd15060dd53542b31dd8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66HBBG2LPJABH3YVXPAZF2DLMO/bundle.json","state_url":"https://pith.science/pith/66HBBG2LPJABH3YVXPAZF2DLMO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66HBBG2LPJABH3YVXPAZF2DLMO/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":"2026-07-06T22:04:33Z","links":{"resolver":"https://pith.science/pith/66HBBG2LPJABH3YVXPAZF2DLMO","bundle":"https://pith.science/pith/66HBBG2LPJABH3YVXPAZF2DLMO/bundle.json","state":"https://pith.science/pith/66HBBG2LPJABH3YVXPAZF2DLMO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66HBBG2LPJABH3YVXPAZF2DLMO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:66HBBG2LPJABH3YVXPAZF2DLMO","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":"9e00ce0fbb778b73583b201d394e0488be5cf233a9394e61d5122058b7b64e60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T15:46:54Z","title_canon_sha256":"8e6beb1c41b1db3a49f86c45d0dd824451d461c7d2ab96710d52dffa1538a41b"},"schema_version":"1.0","source":{"id":"2106.13112","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13112","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13112v2","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13112","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_12","alias_value":"66HBBG2LPJAB","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_16","alias_value":"66HBBG2LPJABH3YV","created_at":"2026-07-05T02:52:46Z"},{"alias_kind":"pith_short_8","alias_value":"66HBBG2L","created_at":"2026-07-05T02:52:46Z"}],"graph_snapshots":[{"event_id":"sha256:df1f80fb7bc2d242151277c83f1c66f4508208fb3f5bd15060dd53542b31dd8c","target":"graph","created_at":"2026-07-05T02:52:46Z","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/2106.13112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual recognition has been dominated by convolutional neural networks (CNNs) for years. Though recently the prevailing vision transformers (ViTs) have shown great potential of self-attention based models in ImageNet classification, their performance is still inferior to that of the latest SOTA CNNs if no extra data are provided. In this work, we try to close the performance gap and demonstrate that attention-based models are indeed able to outperform CNNs. We find a major factor limiting the performance of ViTs for ImageNet classification is their low efficacy in encoding fine-level features ","authors_text":"Jiashi Feng, Li Yuan, Qibin Hou, Shuicheng Yan, Zihang Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T15:46:54Z","title":"VOLO: Vision Outlooker for Visual Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13112","kind":"arxiv","version":2},"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:f90690a26ed6ea034c587e413bc61ccc570113230db4caa45ec9f0a6685e5d45","target":"record","created_at":"2026-07-05T02:52:46Z","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":"9e00ce0fbb778b73583b201d394e0488be5cf233a9394e61d5122058b7b64e60","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-24T15:46:54Z","title_canon_sha256":"8e6beb1c41b1db3a49f86c45d0dd824451d461c7d2ab96710d52dffa1538a41b"},"schema_version":"1.0","source":{"id":"2106.13112","kind":"arxiv","version":2}},"canonical_sha256":"f78e109b4b7a4013ef15bbc192e86b63b7bb2aa5145b3ed62a6664349719ab33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f78e109b4b7a4013ef15bbc192e86b63b7bb2aa5145b3ed62a6664349719ab33","first_computed_at":"2026-07-05T02:52:46.249415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:46.249415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G0Zh4szbtpfjUYvpHYRupijOdbBHjdwy0NDJ+XqIDs0r67zpeceC1sw86iXlcpqFh7SSCWMc3jBHgGzdVfjGDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:46.249871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13112","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f90690a26ed6ea034c587e413bc61ccc570113230db4caa45ec9f0a6685e5d45","sha256:df1f80fb7bc2d242151277c83f1c66f4508208fb3f5bd15060dd53542b31dd8c"],"state_sha256":"04742f43d5ee3e171e15b8e6d7681a3ce3606b3ef3eda7e2c9729f600fa3185b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r76Q9kSBsbwgprYSzq+endVTsHfUsBynp5gkZSKDjkWA6DZ7cWVK1VB1FyyDtxHY2pAw7F1K5QvIx2j6cN6hAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T22:04:33.687357Z","bundle_sha256":"2657a94a816dcfb2c1ce5a55a6ef23ce920ceb1785803c995db65f4766b1e23b"}}