{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NIY6GFRMY2YIBMRXBS7YMANADX","short_pith_number":"pith:NIY6GFRM","schema_version":"1.0","canonical_sha256":"6a31e3162cc6b080b2370cbf8601a01dc92b2fc30982bc2664d7a6905956f54a","source":{"kind":"arxiv","id":"2304.06718","version":4},"attestation_state":"computed","paper":{"title":"Segment Everything Everywhere All at Once","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Li, Hao Zhang, Jianfeng Gao, Jianfeng Wang, Jianwei Yang, Lijuan Wang, Linjie Li, Xueyan Zou, Yong Jae Lee","submitted_at":"2023-04-13T17:59:40Z","abstract_excerpt":"In this work, we present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image, as shown in Fig.1. In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs). More specifically, SEEM is designed with four desiderata: i) Versatility. We introduce a new visual prompt to unify different spatial queries including points, boxes, scribbles and masks, which can further generalize to a different referring ima"},"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":"2304.06718","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:59:40Z","cross_cats_sorted":[],"title_canon_sha256":"184d363b930b744c5b4e3b8ec30d7d459600ab2926e5bdd53c8dec6d9442e460","abstract_canon_sha256":"7f8101d3f2daca951668e7afe6672d3939799086e24acfbdd0f77e9b0013a0bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:06.500573Z","signature_b64":"8Ii3nGAc3UtOf1SWN4yDlJmypY/0UozbvYwsuhfqdY2HKhl6W8BWuJZ3PR5Zd2HD1nZH0L6OAXR6lG4ieKAzBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a31e3162cc6b080b2370cbf8601a01dc92b2fc30982bc2664d7a6905956f54a","last_reissued_at":"2026-07-05T06:30:06.500161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:06.500161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Segment Everything Everywhere All at Once","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Li, Hao Zhang, Jianfeng Gao, Jianfeng Wang, Jianwei Yang, Lijuan Wang, Linjie Li, Xueyan Zou, Yong Jae Lee","submitted_at":"2023-04-13T17:59:40Z","abstract_excerpt":"In this work, we present SEEM, a promptable and interactive model for segmenting everything everywhere all at once in an image, as shown in Fig.1. In SEEM, we propose a novel decoding mechanism that enables diverse prompting for all types of segmentation tasks, aiming at a universal segmentation interface that behaves like large language models (LLMs). More specifically, SEEM is designed with four desiderata: i) Versatility. We introduce a new visual prompt to unify different spatial queries including points, boxes, scribbles and masks, which can further generalize to a different referring ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06718","kind":"arxiv","version":4},"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/2304.06718/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":"2304.06718","created_at":"2026-07-05T06:30:06.500221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06718v4","created_at":"2026-07-05T06:30:06.500221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06718","created_at":"2026-07-05T06:30:06.500221+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIY6GFRMY2YI","created_at":"2026-07-05T06:30:06.500221+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIY6GFRMY2YIBMRX","created_at":"2026-07-05T06:30:06.500221+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIY6GFRM","created_at":"2026-07-05T06:30:06.500221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":169,"is_internal_anchor":false},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2303.16199","citing_title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11441","citing_title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10355","citing_title":"Evaluating Object Hallucination in Large Vision-Language Models","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX","json":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX.json","graph_json":"https://pith.science/api/pith-number/NIY6GFRMY2YIBMRXBS7YMANADX/graph.json","events_json":"https://pith.science/api/pith-number/NIY6GFRMY2YIBMRXBS7YMANADX/events.json","paper":"https://pith.science/paper/NIY6GFRM"},"agent_actions":{"view_html":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX","download_json":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX.json","view_paper":"https://pith.science/paper/NIY6GFRM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06718&json=true","fetch_graph":"https://pith.science/api/pith-number/NIY6GFRMY2YIBMRXBS7YMANADX/graph.json","fetch_events":"https://pith.science/api/pith-number/NIY6GFRMY2YIBMRXBS7YMANADX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX/action/storage_attestation","attest_author":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX/action/author_attestation","sign_citation":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX/action/citation_signature","submit_replication":"https://pith.science/pith/NIY6GFRMY2YIBMRXBS7YMANADX/action/replication_record"}},"created_at":"2026-07-05T06:30:06.500221+00:00","updated_at":"2026-07-05T06:30:06.500221+00:00"}