{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4GLJXI5JPS4MZNURHLUHQAO3NL","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":"2aa97a191efa38d07e8d44268ac9beca29171bdccd5303c86c8e265ad26bad3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T03:02:09Z","title_canon_sha256":"a705bef5185fd81fd1cb1e880b90e91ddfc03fdb8840806054445e8f6d36f96f"},"schema_version":"1.0","source":{"id":"2606.04385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04385","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04385v1","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04385","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_12","alias_value":"4GLJXI5JPS4M","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_16","alias_value":"4GLJXI5JPS4MZNUR","created_at":"2026-06-04T01:09:06Z"},{"alias_kind":"pith_short_8","alias_value":"4GLJXI5J","created_at":"2026-06-04T01:09:06Z"}],"graph_snapshots":[{"event_id":"sha256:36cfb8268f22c382dac32ef390c983f4614ceb5738a7b9e0ba8716df7d308a74","target":"graph","created_at":"2026-06-04T01:09:06Z","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/2606.04385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose GPUA (Geometry-Preserving Unsupervised Alignment), a framework that integrates the complementary strengths of VFMs and VLMs. Inspired by cross-lingual alignment, GPUA treats VFM features as a visual language and lea","authors_text":"Huafeng Li, Shuwen Yu, Yi Zhao, Yonghang Tai, Zhanxuan Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T03:02:09Z","title":"Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04385","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":"sha256:4e6772595d65d208668df5a796480e95cd90046ee426f36fd0deb8ce542ff7c8","target":"record","created_at":"2026-06-04T01:09:06Z","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":"2aa97a191efa38d07e8d44268ac9beca29171bdccd5303c86c8e265ad26bad3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-03T03:02:09Z","title_canon_sha256":"a705bef5185fd81fd1cb1e880b90e91ddfc03fdb8840806054445e8f6d36f96f"},"schema_version":"1.0","source":{"id":"2606.04385","kind":"arxiv","version":1}},"canonical_sha256":"e1969ba3a97cb8ccb6913ae87801db6aebabe0a911aa3efe081100e8e00009a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1969ba3a97cb8ccb6913ae87801db6aebabe0a911aa3efe081100e8e00009a2","first_computed_at":"2026-06-04T01:09:06.088284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:06.088284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZGq3fvhXm3lEN4IZiAE4eGNA3oF3+LuR6UxxrMj0cB7SgIJMfQjJL18znmPbZHErd11eVj2MdLws2jkfQebvCA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:06.088718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e6772595d65d208668df5a796480e95cd90046ee426f36fd0deb8ce542ff7c8","sha256:36cfb8268f22c382dac32ef390c983f4614ceb5738a7b9e0ba8716df7d308a74"],"state_sha256":"9145884df1afd51269509ffdb6dd94682434a74913bcedbdcdfcd3cd6a2d5e79"}