{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QGK4FA3E73ODQORY3NJH2KMUYN","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":"64b851c31bf2960e88a5266cef2c0a8b9d7d8516604405da4052a1b925b93ff0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:21:57Z","title_canon_sha256":"5f203d666209809cda12d06b3172103b63dd716a405db02a1783b976eb340f82"},"schema_version":"1.0","source":{"id":"2310.15308","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15308","created_at":"2026-07-05T08:29:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15308v4","created_at":"2026-07-05T08:29:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15308","created_at":"2026-07-05T08:29:45Z"},{"alias_kind":"pith_short_12","alias_value":"QGK4FA3E73OD","created_at":"2026-07-05T08:29:45Z"},{"alias_kind":"pith_short_16","alias_value":"QGK4FA3E73ODQORY","created_at":"2026-07-05T08:29:45Z"},{"alias_kind":"pith_short_8","alias_value":"QGK4FA3E","created_at":"2026-07-05T08:29:45Z"}],"graph_snapshots":[{"event_id":"sha256:8c6328b855adf1c6041ea17a9fa6a514a9bf7a5a1effcf38a685594b3f1b6188","target":"graph","created_at":"2026-07-05T08:29:45Z","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/2310.15308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their pre-training objectives. For instance, CLIP excels in semantic understanding, while SAM specializes in spatial understanding for segmentation. In this work, we introduce a simple recipe to efficiently merge VFMs into a unified model that absorbs their expertise. Our method integrates techniques of multi-task learning, continual learning, and distillation. Further, it demands significantly less c","authors_text":"Fartash Faghri, Hadi Pouransari, Haoxiang Wang, Mehrdad Farajtabar, Mohammad Rastegari, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Raviteja Vemulapalli, Sachin Mehta","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:21:57Z","title":"SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15308","kind":"arxiv","version":4},"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":"sha256:840ce8014b8e3461ee6eee2d64deeba3fe117adf04a74b8c57c9a51d3caff2dc","target":"record","created_at":"2026-07-05T08:29:45Z","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":"64b851c31bf2960e88a5266cef2c0a8b9d7d8516604405da4052a1b925b93ff0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T19:21:57Z","title_canon_sha256":"5f203d666209809cda12d06b3172103b63dd716a405db02a1783b976eb340f82"},"schema_version":"1.0","source":{"id":"2310.15308","kind":"arxiv","version":4}},"canonical_sha256":"8195c28364fedc383a38db527d2994c357eeb69697a271b603dafe6c385c472e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8195c28364fedc383a38db527d2994c357eeb69697a271b603dafe6c385c472e","first_computed_at":"2026-07-05T08:29:45.079698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:45.079698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/DiOGOYJOFasU1atFrZpKft9Fn2QigYRBcXIFohzVB+QtMsu7Bame20b7dgVxUi9T7vzMcNj6Jv+QsvwBMLCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:45.080149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15308","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:840ce8014b8e3461ee6eee2d64deeba3fe117adf04a74b8c57c9a51d3caff2dc","sha256:8c6328b855adf1c6041ea17a9fa6a514a9bf7a5a1effcf38a685594b3f1b6188"],"state_sha256":"5ca0299575248de22dc81631cb6590f1af3af752c706d5281205d50972288092"}