{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:K6SWUVHUZ2JNNKXD4RGYXEKYYF","short_pith_number":"pith:K6SWUVHU","canonical_record":{"source":{"id":"2305.00729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T09:12:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"efb4ba534e54441c47348d2f9982b5b21eb839a16892a3b21066692655f5dce2","abstract_canon_sha256":"373371b07b62c02f1347f9cd8d4e4906f454897a332753cf386d20d89b512ccb"},"schema_version":"1.0"},"canonical_sha256":"57a56a54f4ce92d6aae3e44d8b9158c15a7f772c8dc3f25bb26fae4faed6fb3c","source":{"kind":"arxiv","id":"2305.00729","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00729","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00729v1","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00729","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"K6SWUVHUZ2JN","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"K6SWUVHUZ2JNNKXD","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"K6SWUVHU","created_at":"2026-07-05T06:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:K6SWUVHUZ2JNNKXD4RGYXEKYYF","target":"record","payload":{"canonical_record":{"source":{"id":"2305.00729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T09:12:30Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"efb4ba534e54441c47348d2f9982b5b21eb839a16892a3b21066692655f5dce2","abstract_canon_sha256":"373371b07b62c02f1347f9cd8d4e4906f454897a332753cf386d20d89b512ccb"},"schema_version":"1.0"},"canonical_sha256":"57a56a54f4ce92d6aae3e44d8b9158c15a7f772c8dc3f25bb26fae4faed6fb3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:44.500601Z","signature_b64":"HZf6czwqQNUQa3iPNG/jqbGKVNJukfusYt46cXof4iJw50r6G2u1QpO0f8Av8BAONYKq/cmry+4e9K9sPoVIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57a56a54f4ce92d6aae3e44d8b9158c15a7f772c8dc3f25bb26fae4faed6fb3c","last_reissued_at":"2026-07-05T06:05:44.500156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:44.500156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.00729","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pWKMB5P75P7IDE9OU7YXDSc6S0nu6Efo2j13LULYYSX2xrRtuAQyMxy6mCEMIhBKRogZYoXxcX0PcfHBiVwdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T00:10:24.062979Z"},"content_sha256":"14f7cd4acb24cf43266a1321f81981cb0a260d8b9d6476cbdc2eaf64a81aaae0","schema_version":"1.0","event_id":"sha256:14f7cd4acb24cf43266a1321f81981cb0a260d8b9d6476cbdc2eaf64a81aaae0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:K6SWUVHUZ2JNNKXD4RGYXEKYYF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Do Self-Supervised Vision Transformers Learn?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Byeongho Heo, Namuk Park, Sangdoo Yun, Taekyung Kim, Wonjae Kim","submitted_at":"2023-05-01T09:12:30Z","abstract_excerpt":"We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision Transformers (ViTs) have the following properties: (1) CL trains self-attentions to capture longer-range global patterns than MIM, such as the shape of an object, especially in the later layers of the ViT architecture. This CL property helps ViTs linearly separate images in their representation spaces. However, it also makes the self-attentions collapse into"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00729","kind":"arxiv","version":1},"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/2305.00729/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":"2026-07-05T06:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IQmJnT2QUJdnk8Iv7Tb+mQ2NBPlZLeBsNePqvb5dKcnn5afc1CVhAD5y7AWCnYHNlWtRDJPeVR+DrHVM9GYLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T00:10:24.063351Z"},"content_sha256":"ec823d26570d7cf034ae0fa1391af454cc078cfa54380e1d982ed8d9e4c4de41","schema_version":"1.0","event_id":"sha256:ec823d26570d7cf034ae0fa1391af454cc078cfa54380e1d982ed8d9e4c4de41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF/bundle.json","state_url":"https://pith.science/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF/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":"2026-07-14T00:10:24Z","links":{"resolver":"https://pith.science/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF","bundle":"https://pith.science/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF/bundle.json","state":"https://pith.science/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6SWUVHUZ2JNNKXD4RGYXEKYYF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K6SWUVHUZ2JNNKXD4RGYXEKYYF","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":"373371b07b62c02f1347f9cd8d4e4906f454897a332753cf386d20d89b512ccb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T09:12:30Z","title_canon_sha256":"efb4ba534e54441c47348d2f9982b5b21eb839a16892a3b21066692655f5dce2"},"schema_version":"1.0","source":{"id":"2305.00729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.00729","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2305.00729v1","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00729","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"K6SWUVHUZ2JN","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"K6SWUVHUZ2JNNKXD","created_at":"2026-07-05T06:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"K6SWUVHU","created_at":"2026-07-05T06:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:ec823d26570d7cf034ae0fa1391af454cc078cfa54380e1d982ed8d9e4c4de41","target":"graph","created_at":"2026-07-05T06:05:44Z","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/2305.00729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision Transformers (ViTs) have the following properties: (1) CL trains self-attentions to capture longer-range global patterns than MIM, such as the shape of an object, especially in the later layers of the ViT architecture. This CL property helps ViTs linearly separate images in their representation spaces. However, it also makes the self-attentions collapse into","authors_text":"Byeongho Heo, Namuk Park, Sangdoo Yun, Taekyung Kim, Wonjae Kim","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T09:12:30Z","title":"What Do Self-Supervised Vision Transformers Learn?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00729","kind":"arxiv","version":1},"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":"sha256:14f7cd4acb24cf43266a1321f81981cb0a260d8b9d6476cbdc2eaf64a81aaae0","target":"record","created_at":"2026-07-05T06:05:44Z","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":"373371b07b62c02f1347f9cd8d4e4906f454897a332753cf386d20d89b512ccb","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-01T09:12:30Z","title_canon_sha256":"efb4ba534e54441c47348d2f9982b5b21eb839a16892a3b21066692655f5dce2"},"schema_version":"1.0","source":{"id":"2305.00729","kind":"arxiv","version":1}},"canonical_sha256":"57a56a54f4ce92d6aae3e44d8b9158c15a7f772c8dc3f25bb26fae4faed6fb3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57a56a54f4ce92d6aae3e44d8b9158c15a7f772c8dc3f25bb26fae4faed6fb3c","first_computed_at":"2026-07-05T06:05:44.500156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:44.500156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HZf6czwqQNUQa3iPNG/jqbGKVNJukfusYt46cXof4iJw50r6G2u1QpO0f8Av8BAONYKq/cmry+4e9K9sPoVIAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:44.500601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.00729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14f7cd4acb24cf43266a1321f81981cb0a260d8b9d6476cbdc2eaf64a81aaae0","sha256:ec823d26570d7cf034ae0fa1391af454cc078cfa54380e1d982ed8d9e4c4de41"],"state_sha256":"8f464f652ed4e7ab3006cb76230769f4883a7ca145e98685ab38fa1a96181c81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zbZfewCTm9Dbv0TNNqxyNej19FB+30jLcQCV3HtSXGFRIUdHqlIqLBOxsubZT1htyCSCHGtMKYRW7oh2UJeCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T00:10:24.065415Z","bundle_sha256":"e3b4743d006c164968d2cb401ed5c79a4126629d40f9da89a5ec9644735ee021"}}