{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W4BHZ2GUKTSASGIJZKI4PO2NQP","short_pith_number":"pith:W4BHZ2GU","canonical_record":{"source":{"id":"2401.02955","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T18:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"70b34c6f48aa50d552c9562b5fce54b4e58fdc207e50a5a8ff9106a229c9d348","abstract_canon_sha256":"a2bdd42528ea068e30d3c0fd161796dd67280af04f2fcf796e3075cc5ec5db28"},"schema_version":"1.0"},"canonical_sha256":"b7027ce8d454e4091909ca91c7bb4d83e5ffae86d9ab99edb413422a8d930e53","source":{"kind":"arxiv","id":"2401.02955","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W4BHZ2GUKTSASGIJZKI4PO2NQP","target":"record","payload":{"canonical_record":{"source":{"id":"2401.02955","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T18:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"70b34c6f48aa50d552c9562b5fce54b4e58fdc207e50a5a8ff9106a229c9d348","abstract_canon_sha256":"a2bdd42528ea068e30d3c0fd161796dd67280af04f2fcf796e3075cc5ec5db28"},"schema_version":"1.0"},"canonical_sha256":"b7027ce8d454e4091909ca91c7bb4d83e5ffae86d9ab99edb413422a8d930e53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:56.695461Z","signature_b64":"kd/a0DrWoV5u2DN3AaLiFFlkVpbFeKJAYCOojQTZczFZGbrMJ1YdgBBhd3wGbxeLi7JwUc7m6rzO/OEbVXwdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7027ce8d454e4091909ca91c7bb4d83e5ffae86d9ab99edb413422a8d930e53","last_reissued_at":"2026-07-05T09:06:56.695004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:56.695004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.02955","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:06:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KOsWuGMNc/8Ait/hg4Z0PKQl1X9Bzkg9pb+XdpgyWqeeIJz2gp3hYRWebxzSMaFi9BqmVwT2G+bw4Fj8S5izDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:41:39.891380Z"},"content_sha256":"27233d6fc8400ea014173c1702c5d7d983d19938654191749ccb06a97d0bf111","schema_version":"1.0","event_id":"sha256:27233d6fc8400ea014173c1702c5d7d983d19938654191749ccb06a97d0bf111"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W4BHZ2GUKTSASGIJZKI4PO2NQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Chong Zhou, Haobo Yuan, Kai Chen, Xiangtai Li, Yining Li","submitted_at":"2024-01-05T18:59:22Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.02955","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.02955/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:06:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ET/b0y1LaM9Wl0lmlzEAOmsnA6fCudGBfW08kKYv7DpUhvx2/h5wc+2478azu1p4GjeSd7VZul7UGGmnpqafAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T07:41:39.891887Z"},"content_sha256":"877d2df5a1de5007e23f2d473571a0726df1dea2668a9532a313157943b76eef","schema_version":"1.0","event_id":"sha256:877d2df5a1de5007e23f2d473571a0726df1dea2668a9532a313157943b76eef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP/bundle.json","state_url":"https://pith.science/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T07:41:39Z","links":{"resolver":"https://pith.science/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP","bundle":"https://pith.science/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP/bundle.json","state":"https://pith.science/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W4BHZ2GUKTSASGIJZKI4PO2NQP/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QqxvIrhmItKprUokpz3IUPNA/RzwnIdo75PMMlBUzLFnyoHjSuLs/mHhWFa0M7kDYiSzA7VZcJadOYA/bJbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T07:41:39.895815Z","bundle_sha256":"9910978a2548329960b67e5a57b2908c4b0da90635ff9792020ae43775a3a1cc"}}