{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5X7IJL7LYJVQF343T7SS2YTHUR","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":"583eebaf35a2844d9aeb0e28b847ac99bf44f3cc93f82be44571b91666a45964","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:58:37Z","title_canon_sha256":"ade6af34774c2b941014d454459bdd6aeb697a62f3d0bcd4610fd9c2ff9ccc4a"},"schema_version":"1.0","source":{"id":"2503.19903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19903","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19903v2","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19903","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"pith_short_12","alias_value":"5X7IJL7LYJVQ","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"pith_short_16","alias_value":"5X7IJL7LYJVQF343","created_at":"2026-07-05T11:47:20Z"},{"alias_kind":"pith_short_8","alias_value":"5X7IJL7L","created_at":"2026-07-05T11:47:20Z"}],"graph_snapshots":[{"event_id":"sha256:dca8b79a1004b6724af7ded67066390288eedb1f9d25f419715418d03646d0c2","target":"graph","created_at":"2026-07-05T11:47:20Z","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/2503.19903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-resolution perception of visual details is crucial for daily tasks. Current vision pre-training, however, is still limited to low resolutions (e.g., 378 x 378 pixels) due to the quadratic cost of processing larger images. We introduce PS3 that scales CLIP-style vision pre-training to 4K resolution with a near-constant cost. Instead of contrastive learning on global image representation, PS3 is pre-trained by selectively processing local regions and contrasting them with local detailed captions, enabling high-resolution representation learning with greatly reduced computational overhead. T","authors_text":"Baifeng Shi, Boyi Li, Han Cai, Hongxu Yin, Jan Kautz, Marco Pavone, Pavlo Molchanov, Sifei Liu, Song Han, Trevor Darrell, Yao Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:58:37Z","title":"Scaling Vision Pre-Training to 4K Resolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19903","kind":"arxiv","version":2},"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":"sha256:57a89be2350dc285570e06a6960ed6e639066a5b0e1f15855fd5dbc0da5a4286","target":"record","created_at":"2026-07-05T11:47:20Z","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":"583eebaf35a2844d9aeb0e28b847ac99bf44f3cc93f82be44571b91666a45964","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:58:37Z","title_canon_sha256":"ade6af34774c2b941014d454459bdd6aeb697a62f3d0bcd4610fd9c2ff9ccc4a"},"schema_version":"1.0","source":{"id":"2503.19903","kind":"arxiv","version":2}},"canonical_sha256":"edfe84afebc26b02ef9b9fe52d6267a47217c2b411811170a504f56a75ada3f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edfe84afebc26b02ef9b9fe52d6267a47217c2b411811170a504f56a75ada3f0","first_computed_at":"2026-07-05T11:47:20.802602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:20.802602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UELFE9xFOG2xj9A2tc6+ukr30fJtPkXL3x1gthy6TkAEjnWOJ2hYdqrVBEvxNMsZm7bZ47Rsh1iRvEH10d21Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:20.803102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57a89be2350dc285570e06a6960ed6e639066a5b0e1f15855fd5dbc0da5a4286","sha256:dca8b79a1004b6724af7ded67066390288eedb1f9d25f419715418d03646d0c2"],"state_sha256":"a134649c74e5ad6e25e67f7d5f39ac4ef2fbb9f5098f34ca6d750e19337075cf"}