{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6GCAB457TBMQ6BAGSG6SBMEAOX","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":"62cede5f5f759f4052069097caa73a8dffea81e64a47599d285d38a55ee209ad","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T18:46:08Z","title_canon_sha256":"397bc0af694069326ba484b0add477d567575333ea4eb2a9458c8375ebcc591c"},"schema_version":"1.0","source":{"id":"2504.14032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14032","created_at":"2026-07-05T10:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14032v1","created_at":"2026-07-05T10:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14032","created_at":"2026-07-05T10:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"6GCAB457TBMQ","created_at":"2026-07-05T10:51:09Z"},{"alias_kind":"pith_short_16","alias_value":"6GCAB457TBMQ6BAG","created_at":"2026-07-05T10:51:09Z"},{"alias_kind":"pith_short_8","alias_value":"6GCAB457","created_at":"2026-07-05T10:51:09Z"}],"graph_snapshots":[{"event_id":"sha256:80578cec06af52f0e9b8294c17a7f309175b2a4558d9890f349ab1d29cc935b2","target":"graph","created_at":"2026-07-05T10:51:09Z","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/2504.14032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding. Feature upsampling offers a promising direction to address this challenge. In this work, we identify two critical factors for enhancing feature upsampling: the upsampler architecture and the training objective. For the upsampler architecture, we introduce a coordinate-based cross-attention transformer that integrates the high-resolution images with coordinates and low-r","authors_text":"Andreas Geiger, Anpei Chen, Dan Zhang, Haiwen Huang, Volodymyr Havrylov","cross_cats":["cs.AI","cs.LG","eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T18:46:08Z","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14032","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":"sha256:453e28b5cb1c7d85dd71649436fac044871f81c17579f322d87902f20e148067","target":"record","created_at":"2026-07-05T10:51:09Z","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":"62cede5f5f759f4052069097caa73a8dffea81e64a47599d285d38a55ee209ad","cross_cats_sorted":["cs.AI","cs.LG","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-18T18:46:08Z","title_canon_sha256":"397bc0af694069326ba484b0add477d567575333ea4eb2a9458c8375ebcc591c"},"schema_version":"1.0","source":{"id":"2504.14032","kind":"arxiv","version":1}},"canonical_sha256":"f18400f3bf98590f040691bd20b08075ca6d5f849154e4003ce0cc9b99c481a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f18400f3bf98590f040691bd20b08075ca6d5f849154e4003ce0cc9b99c481a4","first_computed_at":"2026-07-05T10:51:09.881250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:51:09.881250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ZPtAl8AjfF5bNGYQCEWEcUxFmFMGUzFwlLY9ZaaMtmjlLeoqWekJwN5FChpdNCzRXhAPFzrAiYqhlbTby2KCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:51:09.881668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:453e28b5cb1c7d85dd71649436fac044871f81c17579f322d87902f20e148067","sha256:80578cec06af52f0e9b8294c17a7f309175b2a4558d9890f349ab1d29cc935b2"],"state_sha256":"941dfe5a21e65eae87f1943bb424a03923e0ef79ec41bf19d373dd182946ddd7"}