{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W4BHZ2GUKTSASGIJZKI4PO2NQP","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":"a2bdd42528ea068e30d3c0fd161796dd67280af04f2fcf796e3075cc5ec5db28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T18:59:22Z","title_canon_sha256":"70b34c6f48aa50d552c9562b5fce54b4e58fdc207e50a5a8ff9106a229c9d348"},"schema_version":"1.0","source":{"id":"2401.02955","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.02955","created_at":"2026-07-05T09:06:56Z"},{"alias_kind":"arxiv_version","alias_value":"2401.02955v2","created_at":"2026-07-05T09:06:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.02955","created_at":"2026-07-05T09:06:56Z"},{"alias_kind":"pith_short_12","alias_value":"W4BHZ2GUKTSA","created_at":"2026-07-05T09:06:56Z"},{"alias_kind":"pith_short_16","alias_value":"W4BHZ2GUKTSASGIJ","created_at":"2026-07-05T09:06:56Z"},{"alias_kind":"pith_short_8","alias_value":"W4BHZ2GU","created_at":"2026-07-05T09:06:56Z"}],"graph_snapshots":[{"event_id":"sha256:877d2df5a1de5007e23f2d473571a0726df1dea2668a9532a313157943b76eef","target":"graph","created_at":"2026-07-05T09:06:56Z","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/2401.02955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The CLIP and Segment Anything Model (SAM) are remarkable vision foundation models (VFMs). SAM excels in segmentation tasks across diverse domains, whereas CLIP is renowned for its zero-shot recognition capabilities. This paper presents an in-depth exploration of integrating these two models into a unified framework. Specifically, we introduce the Open-Vocabulary SAM, a SAM-inspired model designed for simultaneous interactive segmentation and recognition, leveraging two unique knowledge transfer modules: SAM2CLIP and CLIP2SAM. The former adapts SAM's knowledge into the CLIP via distillation and","authors_text":"Chen Change Loy, Chong Zhou, Haobo Yuan, Kai Chen, Xiangtai Li, Yining Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T18:59:22Z","title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02955","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":"sha256:27233d6fc8400ea014173c1702c5d7d983d19938654191749ccb06a97d0bf111","target":"record","created_at":"2026-07-05T09:06:56Z","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":"a2bdd42528ea068e30d3c0fd161796dd67280af04f2fcf796e3075cc5ec5db28","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T18:59:22Z","title_canon_sha256":"70b34c6f48aa50d552c9562b5fce54b4e58fdc207e50a5a8ff9106a229c9d348"},"schema_version":"1.0","source":{"id":"2401.02955","kind":"arxiv","version":2}},"canonical_sha256":"b7027ce8d454e4091909ca91c7bb4d83e5ffae86d9ab99edb413422a8d930e53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7027ce8d454e4091909ca91c7bb4d83e5ffae86d9ab99edb413422a8d930e53","first_computed_at":"2026-07-05T09:06:56.695004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:56.695004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kd/a0DrWoV5u2DN3AaLiFFlkVpbFeKJAYCOojQTZczFZGbrMJ1YdgBBhd3wGbxeLi7JwUc7m6rzO/OEbVXwdDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:56.695461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.02955","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27233d6fc8400ea014173c1702c5d7d983d19938654191749ccb06a97d0bf111","sha256:877d2df5a1de5007e23f2d473571a0726df1dea2668a9532a313157943b76eef"],"state_sha256":"467b8d760076b8b6f020108d9c1ca739ce87db0e158115cc068ddc8742f0fe13"}