{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DVOGBIMCQNXNJMHDFLTLU76FBK","short_pith_number":"pith:DVOGBIMC","canonical_record":{"source":{"id":"2204.02964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"1a7371b7290961713426e91e4862fc453fbef2c019d12a0d10e8c48afbf25001","abstract_canon_sha256":"b567809ed3555fc7070da3e2e769b46feac84412b7a9888c88becf0dd44a5f4e"},"schema_version":"1.0"},"canonical_sha256":"1d5c60a182836ed4b0e32ae6ba7fc50a836f4c533ea5a877d7de2f5597e907dd","source":{"kind":"arxiv","id":"2204.02964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02964","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02964v2","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02964","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"DVOGBIMCQNXN","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_16","alias_value":"DVOGBIMCQNXNJMHD","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_8","alias_value":"DVOGBIMC","created_at":"2026-07-05T04:24:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DVOGBIMCQNXNJMHDFLTLU76FBK","target":"record","payload":{"canonical_record":{"source":{"id":"2204.02964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"1a7371b7290961713426e91e4862fc453fbef2c019d12a0d10e8c48afbf25001","abstract_canon_sha256":"b567809ed3555fc7070da3e2e769b46feac84412b7a9888c88becf0dd44a5f4e"},"schema_version":"1.0"},"canonical_sha256":"1d5c60a182836ed4b0e32ae6ba7fc50a836f4c533ea5a877d7de2f5597e907dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:40.148057Z","signature_b64":"0XJZKD1AjSQ0nSAjQ7L90l5NIaeJUtd4HyR7kuz2z7zl5Pxf3MTryxUpI0S+EsrBTmk3G1dB/6C4kEEnZ5KuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d5c60a182836ed4b0e32ae6ba7fc50a836f4c533ea5a877d7de2f5597e907dd","last_reissued_at":"2026-07-05T04:24:40.147587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:40.147587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.02964","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":"2026-07-05T04:24:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hTjaLkZDmUpsRVZd4nWiPPKLD6j0/B0B6rqISkFKDwejFm0rEV3aO51NaA1W/u82W+WBOBZmXUO3cmvjue/qCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:32:14.785747Z"},"content_sha256":"f321c47a7c029fa54a515eb4819d10c725a674958dabed05bab5961d6a20b172","schema_version":"1.0","event_id":"sha256:f321c47a7c029fa54a515eb4819d10c725a674958dabed05bab5961d6a20b172"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DVOGBIMCQNXNJMHDFLTLU76FBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shijie Wang, Shusheng Yang, Xinggang Wang, Ying Shan, Yixiao Ge, Yuxin Fang","submitted_at":"2022-04-06T17:59:04Z","abstract_excerpt":"We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT encoder can work surprisingly well in the challenging object-level recognition scenario even with randomly sampled partial observations, e.g., only 25% $\\sim$ 50% of the input embeddings. (ii) In order to construct multi-scale representations for object detection from single-scale ViT, a randomly initialized compact convolutional stem supplants the pre-trained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02964","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/2204.02964/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":"2026-07-05T04:24:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ghde8Xe7/3L4bJuVHjL4nQEi9JBt34OOeCIZtPzT75RUJPlI1nCs5OkCyT1gU30vvJdmuzwwUv2uHNVKSeBYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:32:14.786132Z"},"content_sha256":"943770568b27124ffc6acb1b9df52ff598fd189208d1ccc7e82ecc9b20fd5641","schema_version":"1.0","event_id":"sha256:943770568b27124ffc6acb1b9df52ff598fd189208d1ccc7e82ecc9b20fd5641"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVOGBIMCQNXNJMHDFLTLU76FBK/bundle.json","state_url":"https://pith.science/pith/DVOGBIMCQNXNJMHDFLTLU76FBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVOGBIMCQNXNJMHDFLTLU76FBK/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":"2026-08-05T23:32:14Z","links":{"resolver":"https://pith.science/pith/DVOGBIMCQNXNJMHDFLTLU76FBK","bundle":"https://pith.science/pith/DVOGBIMCQNXNJMHDFLTLU76FBK/bundle.json","state":"https://pith.science/pith/DVOGBIMCQNXNJMHDFLTLU76FBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVOGBIMCQNXNJMHDFLTLU76FBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DVOGBIMCQNXNJMHDFLTLU76FBK","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":"b567809ed3555fc7070da3e2e769b46feac84412b7a9888c88becf0dd44a5f4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:59:04Z","title_canon_sha256":"1a7371b7290961713426e91e4862fc453fbef2c019d12a0d10e8c48afbf25001"},"schema_version":"1.0","source":{"id":"2204.02964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.02964","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"2204.02964v2","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02964","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"DVOGBIMCQNXN","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_16","alias_value":"DVOGBIMCQNXNJMHD","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_8","alias_value":"DVOGBIMC","created_at":"2026-07-05T04:24:40Z"}],"graph_snapshots":[{"event_id":"sha256:943770568b27124ffc6acb1b9df52ff598fd189208d1ccc7e82ecc9b20fd5641","target":"graph","created_at":"2026-07-05T04:24:40Z","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/2204.02964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an approach to efficiently and effectively adapt a masked image modeling (MIM) pre-trained vanilla Vision Transformer (ViT) for object detection, which is based on our two novel observations: (i) A MIM pre-trained vanilla ViT encoder can work surprisingly well in the challenging object-level recognition scenario even with randomly sampled partial observations, e.g., only 25% $\\sim$ 50% of the input embeddings. (ii) In order to construct multi-scale representations for object detection from single-scale ViT, a randomly initialized compact convolutional stem supplants the pre-trained ","authors_text":"Shijie Wang, Shusheng Yang, Xinggang Wang, Ying Shan, Yixiao Ge, Yuxin Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:59:04Z","title":"Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02964","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:f321c47a7c029fa54a515eb4819d10c725a674958dabed05bab5961d6a20b172","target":"record","created_at":"2026-07-05T04:24:40Z","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":"b567809ed3555fc7070da3e2e769b46feac84412b7a9888c88becf0dd44a5f4e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-06T17:59:04Z","title_canon_sha256":"1a7371b7290961713426e91e4862fc453fbef2c019d12a0d10e8c48afbf25001"},"schema_version":"1.0","source":{"id":"2204.02964","kind":"arxiv","version":2}},"canonical_sha256":"1d5c60a182836ed4b0e32ae6ba7fc50a836f4c533ea5a877d7de2f5597e907dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d5c60a182836ed4b0e32ae6ba7fc50a836f4c533ea5a877d7de2f5597e907dd","first_computed_at":"2026-07-05T04:24:40.147587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:40.147587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0XJZKD1AjSQ0nSAjQ7L90l5NIaeJUtd4HyR7kuz2z7zl5Pxf3MTryxUpI0S+EsrBTmk3G1dB/6C4kEEnZ5KuDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:40.148057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.02964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f321c47a7c029fa54a515eb4819d10c725a674958dabed05bab5961d6a20b172","sha256:943770568b27124ffc6acb1b9df52ff598fd189208d1ccc7e82ecc9b20fd5641"],"state_sha256":"fcdf993642bbc09f9d7daa27b628f5b71a712bfa32c66b5f3851d4de528a408c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFLhpeHrgIL3bUrSbJW6/53rqP+8DBFNUeDHRG+28W/6sA9QHut3nuaD/+h4K5r3t+IeFKz+ysSmZKyBgY62Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:32:14.789003Z","bundle_sha256":"eff0031af2a58d3436272972294ffa4bccdada42c5dcfe01a0689a0d97429402"}}