{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YB7F4T2RKXCDING2IJOXQO6JZT","short_pith_number":"pith:YB7F4T2R","canonical_record":{"source":{"id":"2103.11816","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-22T13:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"272472952a973e1c9673f33f087fb118cfc72ec2e6818cc54e99cb57efcaabcd","abstract_canon_sha256":"0367ab365a103f18a0261a6b2e5b5e39215c0d190bd40299c28645847ffcfb0a"},"schema_version":"1.0"},"canonical_sha256":"c07e5e4f5155c43434da425d783bc9cce666398060a80dc8ec43371b3e2a71b1","source":{"kind":"arxiv","id":"2103.11816","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11816","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11816v2","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11816","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"YB7F4T2RKXCD","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"YB7F4T2RKXCDING2","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"YB7F4T2R","created_at":"2026-07-05T02:33:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YB7F4T2RKXCDING2IJOXQO6JZT","target":"record","payload":{"canonical_record":{"source":{"id":"2103.11816","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-22T13:16:12Z","cross_cats_sorted":[],"title_canon_sha256":"272472952a973e1c9673f33f087fb118cfc72ec2e6818cc54e99cb57efcaabcd","abstract_canon_sha256":"0367ab365a103f18a0261a6b2e5b5e39215c0d190bd40299c28645847ffcfb0a"},"schema_version":"1.0"},"canonical_sha256":"c07e5e4f5155c43434da425d783bc9cce666398060a80dc8ec43371b3e2a71b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:31.411426Z","signature_b64":"k4Gwbqo7FsX+5mbR/wObylC3qjffkcARkcR2jBt9PV1hPas1AYWab2R1ASfccvhc9LeyxS8x6lPK8avcakIIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c07e5e4f5155c43434da425d783bc9cce666398060a80dc8ec43371b3e2a71b1","last_reissued_at":"2026-07-05T02:33:31.410947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:31.410947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.11816","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":"2026-07-05T02:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PAhkqNWHvPLmcrsPODiib8C8I4NjedJpDy+2XktsMk3d3rVulXknbBMldSRuVJ4VdbpzducKEuva7+23AOYhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:20:16.641162Z"},"content_sha256":"0ed17238dbdb46995e4d2727d84ab05d3d79c7a6219fce0e592ab937327149fc","schema_version":"1.0","event_id":"sha256:0ed17238dbdb46995e4d2727d84ab05d3d79c7a6219fce0e592ab937327149fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YB7F4T2RKXCDING2IJOXQO6JZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incorporating Convolution Designs into Visual Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Fengwei Yu, Kun Yuan, Shaopeng Guo, Wei Wu, Ziwei Liu","submitted_at":"2021-03-22T13:16:12Z","abstract_excerpt":"Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large amount of training data or extra supervision to obtain comparable performance with convolutional neural networks (CNNs). To overcome these limitations, we analyze the potential drawbacks when directly borrowing Transformer architectures from NLP. Then we propose a new \\textbf{Convolution-enhanced image Transformer (CeiT)} which combines the advantages of CNNs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11816","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/2103.11816/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":"2026-07-05T02:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ogT2rGcWX7lyl2p7INlnf8IOxF0PdCOPVNdZRKYHPUh78lehBfip32haZwSQEzi91Ff6mP3JJ8Zfvou48QmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T02:20:16.641537Z"},"content_sha256":"668a6973591808bf2e7de785bcf036d6a64b589901824f3c22f387064e6d4895","schema_version":"1.0","event_id":"sha256:668a6973591808bf2e7de785bcf036d6a64b589901824f3c22f387064e6d4895"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YB7F4T2RKXCDING2IJOXQO6JZT/bundle.json","state_url":"https://pith.science/pith/YB7F4T2RKXCDING2IJOXQO6JZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YB7F4T2RKXCDING2IJOXQO6JZT/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":"2026-08-04T02:20:16Z","links":{"resolver":"https://pith.science/pith/YB7F4T2RKXCDING2IJOXQO6JZT","bundle":"https://pith.science/pith/YB7F4T2RKXCDING2IJOXQO6JZT/bundle.json","state":"https://pith.science/pith/YB7F4T2RKXCDING2IJOXQO6JZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YB7F4T2RKXCDING2IJOXQO6JZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YB7F4T2RKXCDING2IJOXQO6JZT","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":"0367ab365a103f18a0261a6b2e5b5e39215c0d190bd40299c28645847ffcfb0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-22T13:16:12Z","title_canon_sha256":"272472952a973e1c9673f33f087fb118cfc72ec2e6818cc54e99cb57efcaabcd"},"schema_version":"1.0","source":{"id":"2103.11816","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11816","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11816v2","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11816","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"YB7F4T2RKXCD","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"YB7F4T2RKXCDING2","created_at":"2026-07-05T02:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"YB7F4T2R","created_at":"2026-07-05T02:33:31Z"}],"graph_snapshots":[{"event_id":"sha256:668a6973591808bf2e7de785bcf036d6a64b589901824f3c22f387064e6d4895","target":"graph","created_at":"2026-07-05T02:33:31Z","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/2103.11816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. However, pure Transformer architectures often require a large amount of training data or extra supervision to obtain comparable performance with convolutional neural networks (CNNs). To overcome these limitations, we analyze the potential drawbacks when directly borrowing Transformer architectures from NLP. Then we propose a new \\textbf{Convolution-enhanced image Transformer (CeiT)} which combines the advantages of CNNs","authors_text":"Aojun Zhou, Fengwei Yu, Kun Yuan, Shaopeng Guo, Wei Wu, Ziwei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-22T13:16:12Z","title":"Incorporating Convolution Designs into Visual Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11816","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":"sha256:0ed17238dbdb46995e4d2727d84ab05d3d79c7a6219fce0e592ab937327149fc","target":"record","created_at":"2026-07-05T02:33:31Z","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":"0367ab365a103f18a0261a6b2e5b5e39215c0d190bd40299c28645847ffcfb0a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-22T13:16:12Z","title_canon_sha256":"272472952a973e1c9673f33f087fb118cfc72ec2e6818cc54e99cb57efcaabcd"},"schema_version":"1.0","source":{"id":"2103.11816","kind":"arxiv","version":2}},"canonical_sha256":"c07e5e4f5155c43434da425d783bc9cce666398060a80dc8ec43371b3e2a71b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c07e5e4f5155c43434da425d783bc9cce666398060a80dc8ec43371b3e2a71b1","first_computed_at":"2026-07-05T02:33:31.410947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:31.410947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k4Gwbqo7FsX+5mbR/wObylC3qjffkcARkcR2jBt9PV1hPas1AYWab2R1ASfccvhc9LeyxS8x6lPK8avcakIIDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:31.411426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.11816","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ed17238dbdb46995e4d2727d84ab05d3d79c7a6219fce0e592ab937327149fc","sha256:668a6973591808bf2e7de785bcf036d6a64b589901824f3c22f387064e6d4895"],"state_sha256":"a7b19f35decbc8c15fbfaef1b0b510a7821640faf51e23d69fd63f9b3569e390"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7crjl6IvXB64SN6jX6Kx9rzIf1OWsUoKFsUuC2L0cMaD5KuugMRvjVDorBpj7OZR4MFD9ll/miPCAGEeUospAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T02:20:16.644349Z","bundle_sha256":"d237572faeffb01937e62042453a9e967a7121595c07244af2b29abf168f0c19"}}