{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:F7URNVIWAN3DJBOJ7XN34U7CP7","short_pith_number":"pith:F7URNVIW","canonical_record":{"source":{"id":"2104.02057","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:59:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7667c8373ac414bff9e24bac1fe8c29f2d27e99a3b9865a6b744d5597d1cd014","abstract_canon_sha256":"b8a623b958db4f0c410fb151c3e3146c6b32c6e8bed249af498aa70602091f85"},"schema_version":"1.0"},"canonical_sha256":"2fe916d51603763485c9fddbbe53e27fd9addb58c8d5558ff556004638d4797f","source":{"kind":"arxiv","id":"2104.02057","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02057","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02057v4","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02057","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"F7URNVIWAN3D","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"F7URNVIWAN3DJBOJ","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"F7URNVIW","created_at":"2026-07-05T03:05:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:F7URNVIWAN3DJBOJ7XN34U7CP7","target":"record","payload":{"canonical_record":{"source":{"id":"2104.02057","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:59:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7667c8373ac414bff9e24bac1fe8c29f2d27e99a3b9865a6b744d5597d1cd014","abstract_canon_sha256":"b8a623b958db4f0c410fb151c3e3146c6b32c6e8bed249af498aa70602091f85"},"schema_version":"1.0"},"canonical_sha256":"2fe916d51603763485c9fddbbe53e27fd9addb58c8d5558ff556004638d4797f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:48.901749Z","signature_b64":"2sXpRdA0yL0I1sKS7X3GZShV5bQf11RoWatumLWr6BQ9vZN2yycuKIPcolRRcT1Tvw71ITITBVXR4vqKol7dBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fe916d51603763485c9fddbbe53e27fd9addb58c8d5558ff556004638d4797f","last_reissued_at":"2026-07-05T03:05:48.901222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:48.901222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.02057","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":"2026-07-05T03:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r55Hip0+PcdsnaQ42owwTjFW8nnDziYuSUhfDuFRkq7/ep8pw6g4CtYD4DsKYU1gtx+kS9wXxn/JWMBOkhHhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:25:18.438202Z"},"content_sha256":"03f347397fafc418f99916f84f24c135f17a5083f51feab338c53d11f0066105","schema_version":"1.0","event_id":"sha256:03f347397fafc418f99916f84f24c135f17a5083f51feab338c53d11f0066105"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:F7URNVIWAN3DJBOJ7XN34U7CP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Empirical Study of Training Self-Supervised Vision Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaiming He, Saining Xie, Xinlei Chen","submitted_at":"2021-04-05T17:59:40Z","abstract_excerpt":"This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT). While the training recipes for standard convolutional networks have been highly mature and robust, the recipes for ViT are yet to be built, especially in the self-supervised scenarios where training becomes more challenging. In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT. We observe that instab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02057","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/2104.02057/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":"2026-07-05T03:05:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPrxcwJDyJx1Tofc6dDOqZ+6P/nqf6+pI//Sy+qgAkI5SDgBZXYIugzdz1ndSZczt0O7IBg5ubNH+RmkUs/NCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:25:18.438716Z"},"content_sha256":"d27ef523dd83e7a1a9c39add2d4092e21cf5d8662f4b6cdedfe5892009bc7d7f","schema_version":"1.0","event_id":"sha256:d27ef523dd83e7a1a9c39add2d4092e21cf5d8662f4b6cdedfe5892009bc7d7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7URNVIWAN3DJBOJ7XN34U7CP7/bundle.json","state_url":"https://pith.science/pith/F7URNVIWAN3DJBOJ7XN34U7CP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7URNVIWAN3DJBOJ7XN34U7CP7/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":"2026-08-09T15:25:18Z","links":{"resolver":"https://pith.science/pith/F7URNVIWAN3DJBOJ7XN34U7CP7","bundle":"https://pith.science/pith/F7URNVIWAN3DJBOJ7XN34U7CP7/bundle.json","state":"https://pith.science/pith/F7URNVIWAN3DJBOJ7XN34U7CP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7URNVIWAN3DJBOJ7XN34U7CP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:F7URNVIWAN3DJBOJ7XN34U7CP7","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":"b8a623b958db4f0c410fb151c3e3146c6b32c6e8bed249af498aa70602091f85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:59:40Z","title_canon_sha256":"7667c8373ac414bff9e24bac1fe8c29f2d27e99a3b9865a6b744d5597d1cd014"},"schema_version":"1.0","source":{"id":"2104.02057","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02057","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02057v4","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02057","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_12","alias_value":"F7URNVIWAN3D","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_16","alias_value":"F7URNVIWAN3DJBOJ","created_at":"2026-07-05T03:05:48Z"},{"alias_kind":"pith_short_8","alias_value":"F7URNVIW","created_at":"2026-07-05T03:05:48Z"}],"graph_snapshots":[{"event_id":"sha256:d27ef523dd83e7a1a9c39add2d4092e21cf5d8662f4b6cdedfe5892009bc7d7f","target":"graph","created_at":"2026-07-05T03:05:48Z","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/2104.02057/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper does not describe a novel method. Instead, it studies a straightforward, incremental, yet must-know baseline given the recent progress in computer vision: self-supervised learning for Vision Transformers (ViT). While the training recipes for standard convolutional networks have been highly mature and robust, the recipes for ViT are yet to be built, especially in the self-supervised scenarios where training becomes more challenging. In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT. We observe that instab","authors_text":"Kaiming He, Saining Xie, Xinlei Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:59:40Z","title":"An Empirical Study of Training Self-Supervised Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02057","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":"sha256:03f347397fafc418f99916f84f24c135f17a5083f51feab338c53d11f0066105","target":"record","created_at":"2026-07-05T03:05:48Z","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":"b8a623b958db4f0c410fb151c3e3146c6b32c6e8bed249af498aa70602091f85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:59:40Z","title_canon_sha256":"7667c8373ac414bff9e24bac1fe8c29f2d27e99a3b9865a6b744d5597d1cd014"},"schema_version":"1.0","source":{"id":"2104.02057","kind":"arxiv","version":4}},"canonical_sha256":"2fe916d51603763485c9fddbbe53e27fd9addb58c8d5558ff556004638d4797f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fe916d51603763485c9fddbbe53e27fd9addb58c8d5558ff556004638d4797f","first_computed_at":"2026-07-05T03:05:48.901222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:48.901222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2sXpRdA0yL0I1sKS7X3GZShV5bQf11RoWatumLWr6BQ9vZN2yycuKIPcolRRcT1Tvw71ITITBVXR4vqKol7dBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:48.901749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.02057","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03f347397fafc418f99916f84f24c135f17a5083f51feab338c53d11f0066105","sha256:d27ef523dd83e7a1a9c39add2d4092e21cf5d8662f4b6cdedfe5892009bc7d7f"],"state_sha256":"1c5c89d5fe6fbc5129bd2f76365b0a88f623c6e004fe9190329217c70211bd3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/rX7fO34Vvd9zlQ1MQI8+AUl61MoW16DTPt/DP3NWDJnpHQj0/7Vt3Ikp9E1jmQE02FABRgVbydem2sb4SPBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:25:18.444524Z","bundle_sha256":"50e065f05f0c9ac79e65309e73b6a5b6851aaf241b94619e5071407993c2ada4"}}