{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IIPSAOTXDZYLT5MCHKVSJKCUST","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":"e13d5fc873804567be035079ece35b0a079256132dadd18b5e3224f91ae14a36","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:54:41Z","title_canon_sha256":"d9614fd4f1665bb34babacb937e85559a2640a24f3a6582a33b97f87a90bcc19"},"schema_version":"1.0","source":{"id":"2407.15837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.15837","created_at":"2026-07-05T08:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.15837v1","created_at":"2026-07-05T08:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15837","created_at":"2026-07-05T08:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"IIPSAOTXDZYL","created_at":"2026-07-05T08:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"IIPSAOTXDZYLT5MC","created_at":"2026-07-05T08:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"IIPSAOTX","created_at":"2026-07-05T08:47:02Z"}],"graph_snapshots":[{"event_id":"sha256:3c9021636f2ecd288d08560a5b254d3bedb701be5b4a4eec170bababaf8cd265","target":"graph","created_at":"2026-07-05T08:47:02Z","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/2407.15837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked Image Modeling (MIM) has emerged as a promising method for deriving visual representations from unlabeled image data by predicting missing pixels from masked portions of images. It excels in region-aware learning and provides strong initializations for various tasks, but struggles to capture high-level semantics without further supervised fine-tuning, likely due to the low-level nature of its pixel reconstruction objective. A promising yet unrealized framework is learning representations through masked reconstruction in latent space, combining the locality of MIM with the high-level tar","authors_text":"Abhinav Gupta, Pedro Morgado, Yibing Wei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:54:41Z","title":"Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15837","kind":"arxiv","version":1},"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:ea03a1c0602b1fb08d2c7527bca93f5e4dd767e9eee3c07008025f15f209c1da","target":"record","created_at":"2026-07-05T08:47:02Z","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":"e13d5fc873804567be035079ece35b0a079256132dadd18b5e3224f91ae14a36","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:54:41Z","title_canon_sha256":"d9614fd4f1665bb34babacb937e85559a2640a24f3a6582a33b97f87a90bcc19"},"schema_version":"1.0","source":{"id":"2407.15837","kind":"arxiv","version":1}},"canonical_sha256":"421f203a771e70b9f5823aab24a85494f37fc376414e99b2389d8ff58cf98e2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"421f203a771e70b9f5823aab24a85494f37fc376414e99b2389d8ff58cf98e2a","first_computed_at":"2026-07-05T08:47:02.052949Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:02.052949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xniknm7vABAul8ScXCkND/4KMsv6Qh8qv6cZ4FKK3opbRilBSrKhy/xULp8+oP/5mReNHVOrjfLtVXHgsvqoAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:02.053463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.15837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea03a1c0602b1fb08d2c7527bca93f5e4dd767e9eee3c07008025f15f209c1da","sha256:3c9021636f2ecd288d08560a5b254d3bedb701be5b4a4eec170bababaf8cd265"],"state_sha256":"8d9a6da401d0cb69fa7f93a47b45c0384950505461e9a10540d7e31b4eea6f7b"}