{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PHYZ54FA2EHU6XFRNS6ZZUTF6E","short_pith_number":"pith:PHYZ54FA","schema_version":"1.0","canonical_sha256":"79f19ef0a0d10f4f5cb16cbd9cd265f126828635675d72a90740ba3ed9fb419d","source":{"kind":"arxiv","id":"2306.03514","version":3},"attestation_state":"computed","paper":{"title":"Recognize Anything: A Strong Image Tagging Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinyu Ma, Lei Zhang, Shilong Liu, Tong Luo, Xinyu Huang, Yanchun Xie, Yandong Guo, Yaqian Li, Youcai Zhang, Yuzhuo Qin, Zhaochuan Luo, Zhaoyang Li","submitted_at":"2023-06-06T09:00:10Z","abstract_excerpt":"We present the Recognize Anything Model (RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in computer vision, demonstrating the zero-shot ability to recognize any common category with high accuracy. RAM introduces a new paradigm for image tagging, leveraging large-scale image-text pairs for training instead of manual annotations.\n  The development of RAM comprises four key steps. Firstly, annotation-free image tags are obtained at scale through automatic text semantic parsing. Subsequently, a preliminary model is trained for automatic annotation "},"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":"2306.03514","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-06T09:00:10Z","cross_cats_sorted":[],"title_canon_sha256":"944ea3e15fd3344116550be915454411dc1d8056f773bab55cb21f574f7ac98e","abstract_canon_sha256":"38f93aad8cf582176e5697f8384535c61c0e0d6572a150e6cca23fc95bc0dccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:05.544787Z","signature_b64":"3A4IGdmwkBfRv/XmppjdhCXwuKDGhg27z45fFEYe/tjOJ0bTQ/91ODkUjDFAkperASxDdj3TL9/cZvhziHC/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79f19ef0a0d10f4f5cb16cbd9cd265f126828635675d72a90740ba3ed9fb419d","last_reissued_at":"2026-07-05T06:19:05.544326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:05.544326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recognize Anything: A Strong Image Tagging Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jinyu Ma, Lei Zhang, Shilong Liu, Tong Luo, Xinyu Huang, Yanchun Xie, Yandong Guo, Yaqian Li, Youcai Zhang, Yuzhuo Qin, Zhaochuan Luo, Zhaoyang Li","submitted_at":"2023-06-06T09:00:10Z","abstract_excerpt":"We present the Recognize Anything Model (RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in computer vision, demonstrating the zero-shot ability to recognize any common category with high accuracy. RAM introduces a new paradigm for image tagging, leveraging large-scale image-text pairs for training instead of manual annotations.\n  The development of RAM comprises four key steps. Firstly, annotation-free image tags are obtained at scale through automatic text semantic parsing. Subsequently, a preliminary model is trained for automatic annotation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03514","kind":"arxiv","version":3},"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/2306.03514/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":"2306.03514","created_at":"2026-07-05T06:19:05.544387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03514v3","created_at":"2026-07-05T06:19:05.544387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03514","created_at":"2026-07-05T06:19:05.544387+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHYZ54FA2EHU","created_at":"2026-07-05T06:19:05.544387+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHYZ54FA2EHU6XFR","created_at":"2026-07-05T06:19:05.544387+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHYZ54FA","created_at":"2026-07-05T06:19:05.544387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12849","citing_title":"SemanticXR: Low Power and Real-time Queryable Semantic Mapping with an Object-Level Device-Cloud Architecture","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01072","citing_title":"Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28592","citing_title":"Embodiment Meets Environment: Toward Context-Aware, Safe Physical Caregiving Robots","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07878","citing_title":"A Woman with a Knife or A Knife with a Woman? Measuring Directional Bias Amplification in Image Captions","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21244","citing_title":"SR-Ground: Image Quality Grounding for Super-Resolved Content","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2402.00253","citing_title":"A Survey on Hallucination in Large Vision-Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21915","citing_title":"Vista4D: Video Reshooting with 4D Point Clouds","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19192","citing_title":"Empowering NPC Dialogue with Environmental Context Using LLMs and Panoramic Images","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2401.14159","citing_title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07141","citing_title":"Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18562","citing_title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E","json":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E.json","graph_json":"https://pith.science/api/pith-number/PHYZ54FA2EHU6XFRNS6ZZUTF6E/graph.json","events_json":"https://pith.science/api/pith-number/PHYZ54FA2EHU6XFRNS6ZZUTF6E/events.json","paper":"https://pith.science/paper/PHYZ54FA"},"agent_actions":{"view_html":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E","download_json":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E.json","view_paper":"https://pith.science/paper/PHYZ54FA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03514&json=true","fetch_graph":"https://pith.science/api/pith-number/PHYZ54FA2EHU6XFRNS6ZZUTF6E/graph.json","fetch_events":"https://pith.science/api/pith-number/PHYZ54FA2EHU6XFRNS6ZZUTF6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E/action/storage_attestation","attest_author":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E/action/author_attestation","sign_citation":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E/action/citation_signature","submit_replication":"https://pith.science/pith/PHYZ54FA2EHU6XFRNS6ZZUTF6E/action/replication_record"}},"created_at":"2026-07-05T06:19:05.544387+00:00","updated_at":"2026-07-05T06:19:05.544387+00:00"}