{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PWJADXFCEZH6ATS74KJYUEMU6T","short_pith_number":"pith:PWJADXFC","schema_version":"1.0","canonical_sha256":"7d9201dca2264fe04e5fe2938a1194f4c9d27b862d8720217c7fa83c8f313110","source":{"kind":"arxiv","id":"2501.03005","version":1},"attestation_state":"computed","paper":{"title":"PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eui Jun Hwang, Jong C. Park, Junmyeong Lee, Sukmin Cho","submitted_at":"2025-01-06T13:30:16Z","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 "},"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":"2501.03005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-06T13:30:16Z","cross_cats_sorted":[],"title_canon_sha256":"67c2dd74dff91f09e68d5737d8a809cba3ec8b3bbd47196d379302552372192d","abstract_canon_sha256":"bd5bf316a4721c74a36cc5604ef382b4381db9fce606f3381d92d60a12525b8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:29.094595Z","signature_b64":"AwPuwUZR7qIucC7iSQJc9TiIRGY153QNqqzmj4kKcOOBfKqleSVbPHk+2dpIJ8/Fr9yiTsdM72uM7pfLXt7vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d9201dca2264fe04e5fe2938a1194f4c9d27b862d8720217c7fa83c8f313110","last_reissued_at":"2026-07-05T09:57:29.094170Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:29.094170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PiLaMIM: Toward Richer Visual Representations by Integrating Pixel and Latent Masked Image Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eui Jun Hwang, Jong C. Park, Junmyeong Lee, Sukmin Cho","submitted_at":"2025-01-06T13:30:16Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03005","kind":"arxiv","version":1},"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/2501.03005/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":"2501.03005","created_at":"2026-07-05T09:57:29.094226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.03005v1","created_at":"2026-07-05T09:57:29.094226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03005","created_at":"2026-07-05T09:57:29.094226+00:00"},{"alias_kind":"pith_short_12","alias_value":"PWJADXFCEZH6","created_at":"2026-07-05T09:57:29.094226+00:00"},{"alias_kind":"pith_short_16","alias_value":"PWJADXFCEZH6ATS7","created_at":"2026-07-05T09:57:29.094226+00:00"},{"alias_kind":"pith_short_8","alias_value":"PWJADXFC","created_at":"2026-07-05T09:57:29.094226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T","json":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T.json","graph_json":"https://pith.science/api/pith-number/PWJADXFCEZH6ATS74KJYUEMU6T/graph.json","events_json":"https://pith.science/api/pith-number/PWJADXFCEZH6ATS74KJYUEMU6T/events.json","paper":"https://pith.science/paper/PWJADXFC"},"agent_actions":{"view_html":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T","download_json":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T.json","view_paper":"https://pith.science/paper/PWJADXFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.03005&json=true","fetch_graph":"https://pith.science/api/pith-number/PWJADXFCEZH6ATS74KJYUEMU6T/graph.json","fetch_events":"https://pith.science/api/pith-number/PWJADXFCEZH6ATS74KJYUEMU6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T/action/storage_attestation","attest_author":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T/action/author_attestation","sign_citation":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T/action/citation_signature","submit_replication":"https://pith.science/pith/PWJADXFCEZH6ATS74KJYUEMU6T/action/replication_record"}},"created_at":"2026-07-05T09:57:29.094226+00:00","updated_at":"2026-07-05T09:57:29.094226+00:00"}