{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EMEKERJMFWKOTOOK3BE7CP7NJJ","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":"25690caf35f38d4bc06687d40a0b9ad47a2303d91dd5b9acd4895d6649135643","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:51:39Z","title_canon_sha256":"7849bf102a5aacfeb061a3c17e50591f8a7fa434ba63a9c45662eccb2c31555b"},"schema_version":"1.0","source":{"id":"2506.05302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05302","created_at":"2026-07-05T11:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05302v1","created_at":"2026-07-05T11:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05302","created_at":"2026-07-05T11:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"EMEKERJMFWKO","created_at":"2026-07-05T11:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"EMEKERJMFWKOTOOK","created_at":"2026-07-05T11:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"EMEKERJM","created_at":"2026-07-05T11:16:45Z"}],"graph_snapshots":[{"event_id":"sha256:c44e535f9b24edb790c70be76a55fe59550e794794714437c01c795f8e5f9f31","target":"graph","created_at":"2026-07-05T11:16:45Z","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/2506.05302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present Perceive Anything Model (PAM), a conceptually straightforward and efficient framework for comprehensive region-level visual understanding in images and videos. Our approach extends the powerful segmentation model SAM 2 by integrating Large Language Models (LLMs), enabling simultaneous object segmentation with the generation of diverse, region-specific semantic outputs, including categories, label definition, functional explanations, and detailed captions. A key component, Semantic Perceiver, is introduced to efficiently transform SAM 2's rich visual features, which inherently carry ","authors_text":"Hongsheng Li, Lei Zhang, Renrui Zhang, Ruichuan An, Tianhe Ren, Tingwei Chen, Weifeng Lin, Wentao Zhang, Xinyu Wei, Ziyu Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:51:39Z","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05302","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":"sha256:7696c64b65db20e16f74a2e97b26d9787da306b2c23d26c21caf16233e80fa0d","target":"record","created_at":"2026-07-05T11:16:45Z","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":"25690caf35f38d4bc06687d40a0b9ad47a2303d91dd5b9acd4895d6649135643","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:51:39Z","title_canon_sha256":"7849bf102a5aacfeb061a3c17e50591f8a7fa434ba63a9c45662eccb2c31555b"},"schema_version":"1.0","source":{"id":"2506.05302","kind":"arxiv","version":1}},"canonical_sha256":"2308a2452c2d94e9b9cad849f13fed4a4231a1d868c6226d7b3b267ee36107f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2308a2452c2d94e9b9cad849f13fed4a4231a1d868c6226d7b3b267ee36107f0","first_computed_at":"2026-07-05T11:16:45.517796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:45.517796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xqgiGOhHqhutSxtdo7SErTEx0tz5W60QcytIFPWLur+yYpWy+vALrA7ixbFkBHZI0DQWikh23kJg4Pjz67UbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:45.518475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7696c64b65db20e16f74a2e97b26d9787da306b2c23d26c21caf16233e80fa0d","sha256:c44e535f9b24edb790c70be76a55fe59550e794794714437c01c795f8e5f9f31"],"state_sha256":"33a6a350e9365729a60fcc17430e4f47843ae4c49c35c772c0a04bd668ecf1e1"}