{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P3MSWIMAD67S47ZY7EUKJ3CQ7T","short_pith_number":"pith:P3MSWIMA","canonical_record":{"source":{"id":"2105.04553","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T17:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"707dd6e0b167e6825d97b11bf0f1db77e43979efe63f849dbe3c4628a48fd397","abstract_canon_sha256":"98e8eab94b7835ecf50afd271d17f940ac53fd752c90ca7fedabdbd352cc59fb"},"schema_version":"1.0"},"canonical_sha256":"7ed92b21801fbf2e7f38f928a4ec50fce441f884b428ee3b820c0d85b3e00a21","source":{"kind":"arxiv","id":"2105.04553","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04553","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04553v2","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04553","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"P3MSWIMAD67S","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"pith_short_16","alias_value":"P3MSWIMAD67S47ZY","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"pith_short_8","alias_value":"P3MSWIMA","created_at":"2026-07-05T02:39:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P3MSWIMAD67S47ZY7EUKJ3CQ7T","target":"record","payload":{"canonical_record":{"source":{"id":"2105.04553","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T17:59:45Z","cross_cats_sorted":[],"title_canon_sha256":"707dd6e0b167e6825d97b11bf0f1db77e43979efe63f849dbe3c4628a48fd397","abstract_canon_sha256":"98e8eab94b7835ecf50afd271d17f940ac53fd752c90ca7fedabdbd352cc59fb"},"schema_version":"1.0"},"canonical_sha256":"7ed92b21801fbf2e7f38f928a4ec50fce441f884b428ee3b820c0d85b3e00a21","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:21.966284Z","signature_b64":"5YA0Q7x92xNLmvadnapVP/vw6zdODbtMA3l16T1ZqvOdZgf0tzM+yxat3lstRlz9ub/XfUKIIQqpBjFmdHOJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed92b21801fbf2e7f38f928a4ec50fce441f884b428ee3b820c0d85b3e00a21","last_reissued_at":"2026-07-05T02:39:21.965849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:21.965849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.04553","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":"2026-07-05T02:39:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6q7umvPOP3ahBzOnhg9zSfULntT/k8iWssFY7WzWkueYf4gM28GsexbNUhtXJpOz/t7Wp5SAvEOJecFB2D6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:15:54.750482Z"},"content_sha256":"ef63f6a2f8014e618447aea10a8ada0ab93489803a17b57c3031a5ebec6d2a2d","schema_version":"1.0","event_id":"sha256:ef63f6a2f8014e618447aea10a8ada0ab93489803a17b57c3031a5ebec6d2a2d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P3MSWIMAD67S47ZY7EUKJ3CQ7T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Supervised Learning with Swin Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Hu, Qi Dai, Yue Cao, Yutong Lin, Zhenda Xie, Zheng Zhang, Zhuliang Yao","submitted_at":"2021-05-10T17:59:45Z","abstract_excerpt":"We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach basically has no new inventions, which is combined from MoCo v2 and BYOL and tuned to achieve reasonably high accuracy on ImageNet-1K linear evaluation: 72.8% and 75.0% top-1 accuracy using DeiT-S and Swin-T, respectively, by 300-epoch training. The performance is slightly better than recent works of MoCo v3 and DINO which adopt DeiT as the backbone, but with much lighter tri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04553","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/2105.04553/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":"2026-07-05T02:39:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v6dAsv/h8aWIkEDhAXarnkk3bJzt6zYZ93YnWtSPJ0spxkpyfqAoYilqMasmz7A3XNqDUmDpSO924LW5hOihBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:15:54.751008Z"},"content_sha256":"35c432139a10b0f85be4505bf8f0d5612ac03a96af9b649ceecc5b5e8d917354","schema_version":"1.0","event_id":"sha256:35c432139a10b0f85be4505bf8f0d5612ac03a96af9b649ceecc5b5e8d917354"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T/bundle.json","state_url":"https://pith.science/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T/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":"2026-08-07T17:15:54Z","links":{"resolver":"https://pith.science/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T","bundle":"https://pith.science/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T/bundle.json","state":"https://pith.science/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3MSWIMAD67S47ZY7EUKJ3CQ7T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P3MSWIMAD67S47ZY7EUKJ3CQ7T","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":"98e8eab94b7835ecf50afd271d17f940ac53fd752c90ca7fedabdbd352cc59fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T17:59:45Z","title_canon_sha256":"707dd6e0b167e6825d97b11bf0f1db77e43979efe63f849dbe3c4628a48fd397"},"schema_version":"1.0","source":{"id":"2105.04553","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.04553","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2105.04553v2","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04553","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"P3MSWIMAD67S","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"pith_short_16","alias_value":"P3MSWIMAD67S47ZY","created_at":"2026-07-05T02:39:21Z"},{"alias_kind":"pith_short_8","alias_value":"P3MSWIMA","created_at":"2026-07-05T02:39:21Z"}],"graph_snapshots":[{"event_id":"sha256:35c432139a10b0f85be4505bf8f0d5612ac03a96af9b649ceecc5b5e8d917354","target":"graph","created_at":"2026-07-05T02:39:21Z","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/2105.04553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We are witnessing a modeling shift from CNN to Transformers in computer vision. In this work, we present a self-supervised learning approach called MoBY, with Vision Transformers as its backbone architecture. The approach basically has no new inventions, which is combined from MoCo v2 and BYOL and tuned to achieve reasonably high accuracy on ImageNet-1K linear evaluation: 72.8% and 75.0% top-1 accuracy using DeiT-S and Swin-T, respectively, by 300-epoch training. The performance is slightly better than recent works of MoCo v3 and DINO which adopt DeiT as the backbone, but with much lighter tri","authors_text":"Han Hu, Qi Dai, Yue Cao, Yutong Lin, Zhenda Xie, Zheng Zhang, Zhuliang Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T17:59:45Z","title":"Self-Supervised Learning with Swin Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04553","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:ef63f6a2f8014e618447aea10a8ada0ab93489803a17b57c3031a5ebec6d2a2d","target":"record","created_at":"2026-07-05T02:39:21Z","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":"98e8eab94b7835ecf50afd271d17f940ac53fd752c90ca7fedabdbd352cc59fb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-10T17:59:45Z","title_canon_sha256":"707dd6e0b167e6825d97b11bf0f1db77e43979efe63f849dbe3c4628a48fd397"},"schema_version":"1.0","source":{"id":"2105.04553","kind":"arxiv","version":2}},"canonical_sha256":"7ed92b21801fbf2e7f38f928a4ec50fce441f884b428ee3b820c0d85b3e00a21","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ed92b21801fbf2e7f38f928a4ec50fce441f884b428ee3b820c0d85b3e00a21","first_computed_at":"2026-07-05T02:39:21.965849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:39:21.965849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5YA0Q7x92xNLmvadnapVP/vw6zdODbtMA3l16T1ZqvOdZgf0tzM+yxat3lstRlz9ub/XfUKIIQqpBjFmdHOJAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:39:21.966284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.04553","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef63f6a2f8014e618447aea10a8ada0ab93489803a17b57c3031a5ebec6d2a2d","sha256:35c432139a10b0f85be4505bf8f0d5612ac03a96af9b649ceecc5b5e8d917354"],"state_sha256":"36260fc9ee2b022bfe694534e4a38a7123d7fbc3be3e5c6b8e6a797be571372d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLjIM46QhPZcSFfVLdQV+CWJU2SyPcSxlYWjikIeIpNqHc8ZRKOT0M1QJtpyWmMQqpN/OyLjxoSp6k+m9RsBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:15:54.755654Z","bundle_sha256":"7b7da3416f9af9cbb6b3f5e07d2f4064649a3af096b796532b2481d0261231f2"}}