{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WULO5KYK6UFGIJTVMDGS7DIE3J","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":"e0ad7d258e0567571670fc1e47b97ae32398df11c42b5c7c9a76adb170c920db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T15:12:19Z","title_canon_sha256":"d579b96c237be0e27b9c8ec2a024fb15a42160c5277060a9fce53d0fc9ed96bb"},"schema_version":"1.0","source":{"id":"2205.03892","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.03892","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"arxiv_version","alias_value":"2205.03892v2","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03892","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_12","alias_value":"WULO5KYK6UFG","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_16","alias_value":"WULO5KYK6UFGIJTV","created_at":"2026-07-05T04:24:40Z"},{"alias_kind":"pith_short_8","alias_value":"WULO5KYK","created_at":"2026-07-05T04:24:40Z"}],"graph_snapshots":[{"event_id":"sha256:1453ee809905b34961c414a55406652f176d17b9b17f9b5728e432992de7d592","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/2205.03892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation. In this paper, our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. However, directly using the original masking strategy leads to the heavy computat","authors_text":"Hongsheng Li, Jifeng Dai, Peng Gao, Teli Ma, Yu Qiao, Ziyi Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T15:12:19Z","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03892","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:cbaa1deed4548769733381f4a6c6bb992a89ef1ac5d8fa069394e2d8a05f98e2","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":"e0ad7d258e0567571670fc1e47b97ae32398df11c42b5c7c9a76adb170c920db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-08T15:12:19Z","title_canon_sha256":"d579b96c237be0e27b9c8ec2a024fb15a42160c5277060a9fce53d0fc9ed96bb"},"schema_version":"1.0","source":{"id":"2205.03892","kind":"arxiv","version":2}},"canonical_sha256":"b516eeab0af50a64267560cd2f8d04da42bfa1b2d4cac4020c16dbe70fcb6c82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b516eeab0af50a64267560cd2f8d04da42bfa1b2d4cac4020c16dbe70fcb6c82","first_computed_at":"2026-07-05T04:24:40.744822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:40.744822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"is/9w8zr70tMAg8Fgdol4Em6g9mjXFELtLnXJr7+1WHMDEbk+1t/t0vXOM5/lBws+kFLW7Hmll84F0EGUlc1Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:40.745308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.03892","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbaa1deed4548769733381f4a6c6bb992a89ef1ac5d8fa069394e2d8a05f98e2","sha256:1453ee809905b34961c414a55406652f176d17b9b17f9b5728e432992de7d592"],"state_sha256":"c286da366cbd6beb8489263ff299d16d60a654cf812bce3a97a01cd84558c42d"}