{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LFZ2O5J2FZVUENFA7Q3QJ27GOA","short_pith_number":"pith:LFZ2O5J2","canonical_record":{"source":{"id":"2208.06366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T16:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"716ff212b983ab9a47ade56c57a02144f34dd7c169126f55c7990de1bb60dc5c","abstract_canon_sha256":"8c9061384166c01d26534aadf5ed1614b577a5ec10b9fdb6508d7809243fbca0"},"schema_version":"1.0"},"canonical_sha256":"5973a7753a2e6b4234a0fc3704ebe67007230dc2694fa7a20b9d19be14d9e112","source":{"kind":"arxiv","id":"2208.06366","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06366","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06366v2","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06366","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"LFZ2O5J2FZVU","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"LFZ2O5J2FZVUENFA","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"LFZ2O5J2","created_at":"2026-07-05T05:02:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LFZ2O5J2FZVUENFA7Q3QJ27GOA","target":"record","payload":{"canonical_record":{"source":{"id":"2208.06366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T16:48:10Z","cross_cats_sorted":[],"title_canon_sha256":"716ff212b983ab9a47ade56c57a02144f34dd7c169126f55c7990de1bb60dc5c","abstract_canon_sha256":"8c9061384166c01d26534aadf5ed1614b577a5ec10b9fdb6508d7809243fbca0"},"schema_version":"1.0"},"canonical_sha256":"5973a7753a2e6b4234a0fc3704ebe67007230dc2694fa7a20b9d19be14d9e112","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:44.083724Z","signature_b64":"kcb/4gq4+tCc4Ya9Q3fvcoWqAc8Fx/WZMDP0iEcgueyIXXvJ2TWWUDena3k+9ddnw4QUGCrrZHbFS9qygEtrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5973a7753a2e6b4234a0fc3704ebe67007230dc2694fa7a20b9d19be14d9e112","last_reissued_at":"2026-07-05T05:02:44.083200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:44.083200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.06366","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":"2026-07-05T05:02:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UVDtzhHZYelIeki2i6kdNknBzk+wD++HU0LfwvsIAOUDA+CTGDYDTMHvH9XJE1Fno6wyR3l40yamxrBai/LwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:18.231187Z"},"content_sha256":"c7bdce0fb3e6a72a69ec44098244da756629987c7fc46b99c47668300df4e5c8","schema_version":"1.0","event_id":"sha256:c7bdce0fb3e6a72a69ec44098244da756629987c7fc46b99c47668300df4e5c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LFZ2O5J2FZVUENFA7Q3QJ27GOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Qixiang Ye, Zhiliang Peng","submitted_at":"2022-08-12T16:48:10Z","abstract_excerpt":"Masked image modeling (MIM) has demonstrated impressive results in self-supervised representation learning by recovering corrupted image patches. However, most existing studies operate on low-level image pixels, which hinders the exploitation of high-level semantics for representation models. In this work, we propose to use a semantic-rich visual tokenizer as the reconstruction target for masked prediction, providing a systematic way to promote MIM from pixel-level to semantic-level. Specifically, we propose vector-quantized knowledge distillation to train the tokenizer, which discretizes a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06366","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/2208.06366/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":"2026-07-05T05:02:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XC1MFvH4MpXD5dIBOo3wu+/szLlcJBgV/YvDcJdOrFQUJiMp1e+SYRQffNZjZg7Np7dXLDBSkrfggDzG+zKCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:18.231575Z"},"content_sha256":"43d37ce0f29ef0f3c798e0be9a7f8a436f0214848b9862a98bd46e767a210a02","schema_version":"1.0","event_id":"sha256:43d37ce0f29ef0f3c798e0be9a7f8a436f0214848b9862a98bd46e767a210a02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA/bundle.json","state_url":"https://pith.science/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA/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":"2026-07-06T18:46:18Z","links":{"resolver":"https://pith.science/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA","bundle":"https://pith.science/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA/bundle.json","state":"https://pith.science/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LFZ2O5J2FZVUENFA7Q3QJ27GOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LFZ2O5J2FZVUENFA7Q3QJ27GOA","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":"8c9061384166c01d26534aadf5ed1614b577a5ec10b9fdb6508d7809243fbca0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T16:48:10Z","title_canon_sha256":"716ff212b983ab9a47ade56c57a02144f34dd7c169126f55c7990de1bb60dc5c"},"schema_version":"1.0","source":{"id":"2208.06366","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.06366","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2208.06366v2","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.06366","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"LFZ2O5J2FZVU","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"LFZ2O5J2FZVUENFA","created_at":"2026-07-05T05:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"LFZ2O5J2","created_at":"2026-07-05T05:02:44Z"}],"graph_snapshots":[{"event_id":"sha256:43d37ce0f29ef0f3c798e0be9a7f8a436f0214848b9862a98bd46e767a210a02","target":"graph","created_at":"2026-07-05T05:02:44Z","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/2208.06366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked image modeling (MIM) has demonstrated impressive results in self-supervised representation learning by recovering corrupted image patches. However, most existing studies operate on low-level image pixels, which hinders the exploitation of high-level semantics for representation models. In this work, we propose to use a semantic-rich visual tokenizer as the reconstruction target for masked prediction, providing a systematic way to promote MIM from pixel-level to semantic-level. Specifically, we propose vector-quantized knowledge distillation to train the tokenizer, which discretizes a co","authors_text":"Furu Wei, Hangbo Bao, Li Dong, Qixiang Ye, Zhiliang Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T16:48:10Z","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.06366","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:c7bdce0fb3e6a72a69ec44098244da756629987c7fc46b99c47668300df4e5c8","target":"record","created_at":"2026-07-05T05:02:44Z","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":"8c9061384166c01d26534aadf5ed1614b577a5ec10b9fdb6508d7809243fbca0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-12T16:48:10Z","title_canon_sha256":"716ff212b983ab9a47ade56c57a02144f34dd7c169126f55c7990de1bb60dc5c"},"schema_version":"1.0","source":{"id":"2208.06366","kind":"arxiv","version":2}},"canonical_sha256":"5973a7753a2e6b4234a0fc3704ebe67007230dc2694fa7a20b9d19be14d9e112","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5973a7753a2e6b4234a0fc3704ebe67007230dc2694fa7a20b9d19be14d9e112","first_computed_at":"2026-07-05T05:02:44.083200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:44.083200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kcb/4gq4+tCc4Ya9Q3fvcoWqAc8Fx/WZMDP0iEcgueyIXXvJ2TWWUDena3k+9ddnw4QUGCrrZHbFS9qygEtrBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:44.083724Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.06366","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7bdce0fb3e6a72a69ec44098244da756629987c7fc46b99c47668300df4e5c8","sha256:43d37ce0f29ef0f3c798e0be9a7f8a436f0214848b9862a98bd46e767a210a02"],"state_sha256":"4f41fc45e24dc9743d2ee9395dfc40844792a3f72f67dd4995c701aca44527af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V4fHv6Xul3utVo3/jCrXTwC9V/damtsm0KUJgYmcV0GVZbZR63dnIvcOE5q70GIWtbTTlMwYVPcLR61Z8DqdAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:46:18.233531Z","bundle_sha256":"04c977516f8ff9cea5b8723daec054f463855aec086b704d7c045981fe9adbd4"}}