{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WEXOUBOEAOQ67IZEFDHGSIWCVP","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":"2ce86c158ca02a0e6c8d7fa80316d538bb1d7063c19705ac02205de781ae1c8d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T20:17:10Z","title_canon_sha256":"64ad90edbc64c0173b81e7a243ac70b606586ced9c44bc6a02f7d158dbaab7c2"},"schema_version":"1.0","source":{"id":"2502.08769","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08769","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08769v3","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08769","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"WEXOUBOEAOQ6","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"WEXOUBOEAOQ67IZE","created_at":"2026-07-05T11:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"WEXOUBOE","created_at":"2026-07-05T11:29:06Z"}],"graph_snapshots":[{"event_id":"sha256:2b78f34fecc970539c28a1838b9821f2535edf9f9d29e3cffd55cddbdda31bbf","target":"graph","created_at":"2026-07-05T11:29:06Z","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/2502.08769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked Image Modeling (MIM) offers a promising approach to self-supervised representation learning, however existing MIM models still lag behind the state-of-the-art. In this paper, we systematically analyze target representations, loss functions, and architectures, to introduce CAPI - a novel pure-MIM framework that relies on the prediction of latent clusterings. Our approach leverages a clustering-based loss, which is stable to train, and exhibits promising scaling properties. Our ViT-L backbone, CAPI, achieves 83.8% accuracy on ImageNet and 32.1% mIoU on ADE20K with simple linear probes, su","authors_text":"Federico Baldassarre, Julien Mairal, Maxime Oquab, Piotr Bojanowski, Timoth\\'ee Darcet","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T20:17:10Z","title":"Cluster and Predict Latent Patches for Improved Masked Image Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08769","kind":"arxiv","version":3},"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":"sha256:1c0a406ebe4e5d8aa39862a3b27eed7e01850cea420eb2a94a0606c11079c6c4","target":"record","created_at":"2026-07-05T11:29:06Z","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":"2ce86c158ca02a0e6c8d7fa80316d538bb1d7063c19705ac02205de781ae1c8d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-12T20:17:10Z","title_canon_sha256":"64ad90edbc64c0173b81e7a243ac70b606586ced9c44bc6a02f7d158dbaab7c2"},"schema_version":"1.0","source":{"id":"2502.08769","kind":"arxiv","version":3}},"canonical_sha256":"b12eea05c403a1efa32428ce6922c2abeedcc43a43935101aea759c9d3f9c646","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b12eea05c403a1efa32428ce6922c2abeedcc43a43935101aea759c9d3f9c646","first_computed_at":"2026-07-05T11:29:06.905413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:06.905413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fSIJRln3drzSdvxj0DJo0bd7YoC9AYG2jFIysxlWF97gMsRqrhvNztBty50ogHE1Q5q3M8J/473cELXKuAIjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:06.905923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08769","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c0a406ebe4e5d8aa39862a3b27eed7e01850cea420eb2a94a0606c11079c6c4","sha256:2b78f34fecc970539c28a1838b9821f2535edf9f9d29e3cffd55cddbdda31bbf"],"state_sha256":"a60aa83e89831a5fc3121a1e606c1886ac12e044eeaea57bcc344bb2846bbfcc"}