{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IIPSAOTXDZYLT5MCHKVSJKCUST","short_pith_number":"pith:IIPSAOTX","schema_version":"1.0","canonical_sha256":"421f203a771e70b9f5823aab24a85494f37fc376414e99b2389d8ff58cf98e2a","source":{"kind":"arxiv","id":"2407.15837","version":1},"attestation_state":"computed","paper":{"title":"Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Pedro Morgado, Yibing Wei","submitted_at":"2024-07-22T17:54:41Z","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"},"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":"2407.15837","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-22T17:54:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9614fd4f1665bb34babacb937e85559a2640a24f3a6582a33b97f87a90bcc19","abstract_canon_sha256":"e13d5fc873804567be035079ece35b0a079256132dadd18b5e3224f91ae14a36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:02.053463Z","signature_b64":"xniknm7vABAul8ScXCkND/4KMsv6Qh8qv6cZ4FKK3opbRilBSrKhy/xULp8+oP/5mReNHVOrjfLtVXHgsvqoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421f203a771e70b9f5823aab24a85494f37fc376414e99b2389d8ff58cf98e2a","last_reissued_at":"2026-07-05T08:47:02.052949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:02.052949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Latent Masked Image Modeling for Self-Supervised Visual Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Abhinav Gupta, Pedro Morgado, Yibing Wei","submitted_at":"2024-07-22T17:54:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15837","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/2407.15837/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":"2407.15837","created_at":"2026-07-05T08:47:02.053010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15837v1","created_at":"2026-07-05T08:47:02.053010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15837","created_at":"2026-07-05T08:47:02.053010+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIPSAOTXDZYL","created_at":"2026-07-05T08:47:02.053010+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIPSAOTXDZYLT5MC","created_at":"2026-07-05T08:47:02.053010+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIPSAOTX","created_at":"2026-07-05T08:47:02.053010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06644","citing_title":"Variational Feature Compression for Model-Specific Representations","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST","json":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST.json","graph_json":"https://pith.science/api/pith-number/IIPSAOTXDZYLT5MCHKVSJKCUST/graph.json","events_json":"https://pith.science/api/pith-number/IIPSAOTXDZYLT5MCHKVSJKCUST/events.json","paper":"https://pith.science/paper/IIPSAOTX"},"agent_actions":{"view_html":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST","download_json":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST.json","view_paper":"https://pith.science/paper/IIPSAOTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15837&json=true","fetch_graph":"https://pith.science/api/pith-number/IIPSAOTXDZYLT5MCHKVSJKCUST/graph.json","fetch_events":"https://pith.science/api/pith-number/IIPSAOTXDZYLT5MCHKVSJKCUST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST/action/storage_attestation","attest_author":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST/action/author_attestation","sign_citation":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST/action/citation_signature","submit_replication":"https://pith.science/pith/IIPSAOTXDZYLT5MCHKVSJKCUST/action/replication_record"}},"created_at":"2026-07-05T08:47:02.053010+00:00","updated_at":"2026-07-05T08:47:02.053010+00:00"}