{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EMEKERJMFWKOTOOK3BE7CP7NJJ","short_pith_number":"pith:EMEKERJM","schema_version":"1.0","canonical_sha256":"2308a2452c2d94e9b9cad849f13fed4a4231a1d868c6226d7b3b267ee36107f0","source":{"kind":"arxiv","id":"2506.05302","version":1},"attestation_state":"computed","paper":{"title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Lei Zhang, Renrui Zhang, Ruichuan An, Tianhe Ren, Tingwei Chen, Weifeng Lin, Wentao Zhang, Xinyu Wei, Ziyu Guo","submitted_at":"2025-06-05T17:51:39Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.05302","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:51:39Z","cross_cats_sorted":[],"title_canon_sha256":"7849bf102a5aacfeb061a3c17e50591f8a7fa434ba63a9c45662eccb2c31555b","abstract_canon_sha256":"25690caf35f38d4bc06687d40a0b9ad47a2303d91dd5b9acd4895d6649135643"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:45.518475Z","signature_b64":"xqgiGOhHqhutSxtdo7SErTEx0tz5W60QcytIFPWLur+yYpWy+vALrA7ixbFkBHZI0DQWikh23kJg4Pjz67UbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2308a2452c2d94e9b9cad849f13fed4a4231a1d868c6226d7b3b267ee36107f0","last_reissued_at":"2026-07-05T11:16:45.517796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:45.517796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Lei Zhang, Renrui Zhang, Ruichuan An, Tianhe Ren, Tingwei Chen, Weifeng Lin, Wentao Zhang, Xinyu Wei, Ziyu Guo","submitted_at":"2025-06-05T17:51:39Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05302","kind":"arxiv","version":1},"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/2506.05302/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.05302","created_at":"2026-07-05T11:16:45.517896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05302v1","created_at":"2026-07-05T11:16:45.517896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05302","created_at":"2026-07-05T11:16:45.517896+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMEKERJMFWKO","created_at":"2026-07-05T11:16:45.517896+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMEKERJMFWKOTOOK","created_at":"2026-07-05T11:16:45.517896+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMEKERJM","created_at":"2026-07-05T11:16:45.517896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07433","citing_title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18018","citing_title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16903","citing_title":"WOW-Seg: A Word-free Open World Segmentation Model","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07348","citing_title":"MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12675","citing_title":"Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2602.03151","citing_title":"Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11789","citing_title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ","json":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ.json","graph_json":"https://pith.science/api/pith-number/EMEKERJMFWKOTOOK3BE7CP7NJJ/graph.json","events_json":"https://pith.science/api/pith-number/EMEKERJMFWKOTOOK3BE7CP7NJJ/events.json","paper":"https://pith.science/paper/EMEKERJM"},"agent_actions":{"view_html":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ","download_json":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ.json","view_paper":"https://pith.science/paper/EMEKERJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05302&json=true","fetch_graph":"https://pith.science/api/pith-number/EMEKERJMFWKOTOOK3BE7CP7NJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EMEKERJMFWKOTOOK3BE7CP7NJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ/action/storage_attestation","attest_author":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ/action/author_attestation","sign_citation":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ/action/citation_signature","submit_replication":"https://pith.science/pith/EMEKERJMFWKOTOOK3BE7CP7NJJ/action/replication_record"}},"created_at":"2026-07-05T11:16:45.517896+00:00","updated_at":"2026-07-05T11:16:45.517896+00:00"}