{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JAMNFTZQRXOFBNKV42CYU6NYHY","short_pith_number":"pith:JAMNFTZQ","canonical_record":{"source":{"id":"2206.04667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T17:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"f33b8b8afecf228b8b21c1dc7a4a224061e3597d24ef55d44f5d516038243f66","abstract_canon_sha256":"9f3ace6616166fd57d90a25b9d46dee0d889f900bfa71a796079299b3428b30e"},"schema_version":"1.0"},"canonical_sha256":"4818d2cf308ddc50b555e6858a79b83e03fb0a65b2f675eb09728f56798e685f","source":{"kind":"arxiv","id":"2206.04667","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04667","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04667v2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04667","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"JAMNFTZQRXOF","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"JAMNFTZQRXOFBNKV","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"JAMNFTZQ","created_at":"2026-07-05T05:49:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JAMNFTZQRXOFBNKV42CYU6NYHY","target":"record","payload":{"canonical_record":{"source":{"id":"2206.04667","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T17:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"f33b8b8afecf228b8b21c1dc7a4a224061e3597d24ef55d44f5d516038243f66","abstract_canon_sha256":"9f3ace6616166fd57d90a25b9d46dee0d889f900bfa71a796079299b3428b30e"},"schema_version":"1.0"},"canonical_sha256":"4818d2cf308ddc50b555e6858a79b83e03fb0a65b2f675eb09728f56798e685f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:13.645279Z","signature_b64":"tMhlqf2vZ4VWiXKEokZpeRgNvS2R24JQlwPigzzoREKl/1IILu1fvO3Pp5jra+xpFNfGhydz/pbJedrAb+CnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4818d2cf308ddc50b555e6858a79b83e03fb0a65b2f675eb09728f56798e685f","last_reissued_at":"2026-07-05T05:49:13.644706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:13.644706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.04667","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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zZdQdvQ1K7MKLkUCbDn2uNZjZywTBcULgKYG4/cnV7r6FIUEeXJFgvNqvBLM6gu1Efh/T8kfOokqaizq+FWaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:01:44.642481Z"},"content_sha256":"c8382de36b3ab1920b7ce405aa43ea2fd2350206654d4a4cc8fec3f8edd9a53f","schema_version":"1.0","event_id":"sha256:c8382de36b3ab1920b7ce405aa43ea2fd2350206654d4a4cc8fec3f8edd9a53f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JAMNFTZQRXOFBNKV42CYU6NYHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extreme Masking for Learning Instance and Distributed Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Stephen Lin, Xiao Sun, Zhirong Wu, Zihang Lai","submitted_at":"2022-06-09T17:59:43Z","abstract_excerpt":"The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously. We use self-attention blocks to represent spatially distributed tokens, followed by cross-attention blocks to aggregate the holistic image instance. The core of the approach is the use of extremely large token masking (75\\%-90\\%) as the data augmentation for supervision. Our model, named ExtreMA, follows the plain BYOL approach where the instance representation from the unmasked subset is trained to predict that from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04667","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/2206.04667/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":"2026-07-05T05:49:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ApmR0EVx1084Ymgilpe92cEMzRLYdAKZwTF5CaXFRo6k3BhOpR1nTdGSwMLenhY4Pwrfs1UlBfEL2V7UvnIJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:01:44.643191Z"},"content_sha256":"71cfb5adfbba8a307950bd914839cf1801dd4f523474a230361d5b7b3a8de2fa","schema_version":"1.0","event_id":"sha256:71cfb5adfbba8a307950bd914839cf1801dd4f523474a230361d5b7b3a8de2fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JAMNFTZQRXOFBNKV42CYU6NYHY/bundle.json","state_url":"https://pith.science/pith/JAMNFTZQRXOFBNKV42CYU6NYHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JAMNFTZQRXOFBNKV42CYU6NYHY/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":"2026-08-20T06:01:44Z","links":{"resolver":"https://pith.science/pith/JAMNFTZQRXOFBNKV42CYU6NYHY","bundle":"https://pith.science/pith/JAMNFTZQRXOFBNKV42CYU6NYHY/bundle.json","state":"https://pith.science/pith/JAMNFTZQRXOFBNKV42CYU6NYHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JAMNFTZQRXOFBNKV42CYU6NYHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JAMNFTZQRXOFBNKV42CYU6NYHY","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":"9f3ace6616166fd57d90a25b9d46dee0d889f900bfa71a796079299b3428b30e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T17:59:43Z","title_canon_sha256":"f33b8b8afecf228b8b21c1dc7a4a224061e3597d24ef55d44f5d516038243f66"},"schema_version":"1.0","source":{"id":"2206.04667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04667","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04667v2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04667","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"JAMNFTZQRXOF","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"JAMNFTZQRXOFBNKV","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"JAMNFTZQ","created_at":"2026-07-05T05:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:71cfb5adfbba8a307950bd914839cf1801dd4f523474a230361d5b7b3a8de2fa","target":"graph","created_at":"2026-07-05T05:49:13Z","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/2206.04667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously. We use self-attention blocks to represent spatially distributed tokens, followed by cross-attention blocks to aggregate the holistic image instance. The core of the approach is the use of extremely large token masking (75\\%-90\\%) as the data augmentation for supervision. Our model, named ExtreMA, follows the plain BYOL approach where the instance representation from the unmasked subset is trained to predict that from the ","authors_text":"Stephen Lin, Xiao Sun, Zhirong Wu, Zihang Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T17:59:43Z","title":"Extreme Masking for Learning Instance and Distributed Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04667","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:c8382de36b3ab1920b7ce405aa43ea2fd2350206654d4a4cc8fec3f8edd9a53f","target":"record","created_at":"2026-07-05T05:49:13Z","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":"9f3ace6616166fd57d90a25b9d46dee0d889f900bfa71a796079299b3428b30e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-09T17:59:43Z","title_canon_sha256":"f33b8b8afecf228b8b21c1dc7a4a224061e3597d24ef55d44f5d516038243f66"},"schema_version":"1.0","source":{"id":"2206.04667","kind":"arxiv","version":2}},"canonical_sha256":"4818d2cf308ddc50b555e6858a79b83e03fb0a65b2f675eb09728f56798e685f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4818d2cf308ddc50b555e6858a79b83e03fb0a65b2f675eb09728f56798e685f","first_computed_at":"2026-07-05T05:49:13.644706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:13.644706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tMhlqf2vZ4VWiXKEokZpeRgNvS2R24JQlwPigzzoREKl/1IILu1fvO3Pp5jra+xpFNfGhydz/pbJedrAb+CnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:13.645279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8382de36b3ab1920b7ce405aa43ea2fd2350206654d4a4cc8fec3f8edd9a53f","sha256:71cfb5adfbba8a307950bd914839cf1801dd4f523474a230361d5b7b3a8de2fa"],"state_sha256":"e356a013b8f2ebf8e76bd884eebe0b109db1699ca5d2cbddb91c77095d9d2722"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3naekhGnPv1AjkT8sjq5lenPjZfDRZt2Y01FItUWoEmiJvVvoQMpl+eaPqWL+ifsWAVuJpv7JKmU5uYfKQ7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:01:44.647377Z","bundle_sha256":"095fab30b8686479eb0494f857c7a29df90c1182cb01b16bd2376676430786df"}}