{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PWJADXFCEZH6ATS74KJYUEMU6T","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":"bd5bf316a4721c74a36cc5604ef382b4381db9fce606f3381d92d60a12525b8b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T13:30:16Z","title_canon_sha256":"67c2dd74dff91f09e68d5737d8a809cba3ec8b3bbd47196d379302552372192d"},"schema_version":"1.0","source":{"id":"2501.03005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03005","created_at":"2026-07-05T09:57:29Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03005v1","created_at":"2026-07-05T09:57:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03005","created_at":"2026-07-05T09:57:29Z"},{"alias_kind":"pith_short_12","alias_value":"PWJADXFCEZH6","created_at":"2026-07-05T09:57:29Z"},{"alias_kind":"pith_short_16","alias_value":"PWJADXFCEZH6ATS7","created_at":"2026-07-05T09:57:29Z"},{"alias_kind":"pith_short_8","alias_value":"PWJADXFC","created_at":"2026-07-05T09:57:29Z"}],"graph_snapshots":[{"event_id":"sha256:fb260e1e10c3722cf58ae7c7857f1c7006bc59607c336be9d9a0a1c7f78cc78a","target":"graph","created_at":"2026-07-05T09:57:29Z","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/2501.03005/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Masked Image Modeling (MIM), two primary methods exist: Pixel MIM and Latent MIM, each utilizing different reconstruction targets, raw pixels and latent representations, respectively. Pixel MIM tends to capture low-level visual details such as color and texture, while Latent MIM focuses on high-level semantics of an object. However, these distinct strengths of each method can lead to suboptimal performance in tasks that rely on a particular level of visual features. To address this limitation, we propose PiLaMIM, a unified framework that combines Pixel MIM and Latent MIM to integrate their ","authors_text":"Eui Jun Hwang, Jong C. Park, Junmyeong Lee, Sukmin Cho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T13:30:16Z","title":"PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03005","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":"sha256:40b52ee0898ba086a3c0d7b9a607e5237744fe4cac739a3ce3948d1b5f9d1e1b","target":"record","created_at":"2026-07-05T09:57:29Z","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":"bd5bf316a4721c74a36cc5604ef382b4381db9fce606f3381d92d60a12525b8b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T13:30:16Z","title_canon_sha256":"67c2dd74dff91f09e68d5737d8a809cba3ec8b3bbd47196d379302552372192d"},"schema_version":"1.0","source":{"id":"2501.03005","kind":"arxiv","version":1}},"canonical_sha256":"7d9201dca2264fe04e5fe2938a1194f4c9d27b862d8720217c7fa83c8f313110","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d9201dca2264fe04e5fe2938a1194f4c9d27b862d8720217c7fa83c8f313110","first_computed_at":"2026-07-05T09:57:29.094170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:29.094170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AwPuwUZR7qIucC7iSQJc9TiIRGY153QNqqzmj4kKcOOBfKqleSVbPHk+2dpIJ8/Fr9yiTsdM72uM7pfLXt7vDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:29.094595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40b52ee0898ba086a3c0d7b9a607e5237744fe4cac739a3ce3948d1b5f9d1e1b","sha256:fb260e1e10c3722cf58ae7c7857f1c7006bc59607c336be9d9a0a1c7f78cc78a"],"state_sha256":"3529cd46d131feea7ee08462255410ac07df5e98d64f9b50031424ec61bed45a"}