{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BGW5BDPJW7FDHORY756TKLHCO5","short_pith_number":"pith:BGW5BDPJ","schema_version":"1.0","canonical_sha256":"09add08de9b7ca33ba38ff7d352ce2776660bc4bcbdf1bc9a3a8a647ba132b53","source":{"kind":"arxiv","id":"2205.09616","version":2},"attestation_state":"computed","paper":{"title":"Masked Image Modeling with Denoising Contrast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Jianping Wu, Kun Yi, Shusheng Yang, Xiaohu Qie, Xiaotong Li, Ying Shan, Yixiao Ge","submitted_at":"2022-05-19T15:22:29Z","abstract_excerpt":"Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great poten"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2205.09616","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-19T15:22:29Z","cross_cats_sorted":[],"title_canon_sha256":"0b54703e05a69374df794869f87a24cd1e0ed2fa5a7b650556ca341015df4c99","abstract_canon_sha256":"f313d2ef455160165b02bc24afefd0a7996a1875c79d96a1ee7f47dde935f144"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:30.441402Z","signature_b64":"S1QUsZpxo5NcmrhFXxPnyZ0yzpOZuoUUYLFNiojp/f9HTQj5lYuOANnwrwIwF3+L4dWkey6RM7eA2SdoRmv9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09add08de9b7ca33ba38ff7d352ce2776660bc4bcbdf1bc9a3a8a647ba132b53","last_reissued_at":"2026-07-05T05:36:30.440922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:30.440922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Masked Image Modeling with Denoising Contrast","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Li, Jianping Wu, Kun Yi, Shusheng Yang, Xiaohu Qie, Xiaotong Li, Ying Shan, Yixiao Ge","submitted_at":"2022-05-19T15:22:29Z","abstract_excerpt":"Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision dictionary look-up. MIM recently dominates this line of research with state-of-the-art performance on vision Transformers (ViTs), where the core is to enhance the patch-level visual context capturing of the network via denoising auto-encoding mechanism. Rather than tailoring image tokenizers with extra training stages as in previous works, we unleash the great poten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09616","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/2205.09616/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2205.09616","created_at":"2026-07-05T05:36:30.440977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.09616v2","created_at":"2026-07-05T05:36:30.440977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09616","created_at":"2026-07-05T05:36:30.440977+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGW5BDPJW7FD","created_at":"2026-07-05T05:36:30.440977+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGW5BDPJW7FDHORY","created_at":"2026-07-05T05:36:30.440977+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGW5BDPJ","created_at":"2026-07-05T05:36:30.440977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.14854","citing_title":"Frabjous: Deep Learning Fast Radio Burst Morphologies","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5","json":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5.json","graph_json":"https://pith.science/api/pith-number/BGW5BDPJW7FDHORY756TKLHCO5/graph.json","events_json":"https://pith.science/api/pith-number/BGW5BDPJW7FDHORY756TKLHCO5/events.json","paper":"https://pith.science/paper/BGW5BDPJ"},"agent_actions":{"view_html":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5","download_json":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5.json","view_paper":"https://pith.science/paper/BGW5BDPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.09616&json=true","fetch_graph":"https://pith.science/api/pith-number/BGW5BDPJW7FDHORY756TKLHCO5/graph.json","fetch_events":"https://pith.science/api/pith-number/BGW5BDPJW7FDHORY756TKLHCO5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5/action/storage_attestation","attest_author":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5/action/author_attestation","sign_citation":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5/action/citation_signature","submit_replication":"https://pith.science/pith/BGW5BDPJW7FDHORY756TKLHCO5/action/replication_record"}},"created_at":"2026-07-05T05:36:30.440977+00:00","updated_at":"2026-07-05T05:36:30.440977+00:00"}