{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7B5OBCV5TNQYTYFZWPV7HB4JMY","short_pith_number":"pith:7B5OBCV5","schema_version":"1.0","canonical_sha256":"f87ae08abd9b6189e0b9b3ebf387896638208e47226f5c6c9ed6dd9105e53927","source":{"kind":"arxiv","id":"2310.15200","version":2},"attestation_state":"computed","paper":{"title":"Open-Set Image Tagging with Multi-Grained Text Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Rui Feng, Weiwei Tian, Xinyu Huang, Yanchun Xie, Yaqian Li, Yi-Jie Huang, Youcai Zhang, Yuejie Zhang","submitted_at":"2023-10-23T08:13:33Z","abstract_excerpt":"In this paper, we introduce the Recognize Anything Plus Model (RAM++), an open-set image tagging model effectively leveraging multi-grained text supervision. Previous approaches (e.g., CLIP) primarily utilize global text supervision paired with images, leading to sub-optimal performance in recognizing multiple individual semantic tags. In contrast, RAM++ seamlessly integrates individual tag supervision with global text supervision, all within a unified alignment framework. This integration not only ensures efficient recognition of predefined tag categories, but also enhances generalization cap"},"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":"2310.15200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T08:13:33Z","cross_cats_sorted":[],"title_canon_sha256":"f2eb2c9059433fcccdc9d19bd737b2333c0aa8356f96303a64963d766bbc2319","abstract_canon_sha256":"b09a4354269779c088468af73ee0ed0a3acc485bd3af31adbb89c3a43d3f9dbb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:45.365580Z","signature_b64":"4DQV9hsgKBOmDK+gP1LxCxti4XbmKn/c2DvJ//b4E/rfHn782MUqwmNGY+cEi5+nXDbr4+EC5AlKUewrlwkMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f87ae08abd9b6189e0b9b3ebf387896638208e47226f5c6c9ed6dd9105e53927","last_reissued_at":"2026-07-05T07:13:45.365120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:45.365120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-Set Image Tagging with Multi-Grained Text Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Rui Feng, Weiwei Tian, Xinyu Huang, Yanchun Xie, Yaqian Li, Yi-Jie Huang, Youcai Zhang, Yuejie Zhang","submitted_at":"2023-10-23T08:13:33Z","abstract_excerpt":"In this paper, we introduce the Recognize Anything Plus Model (RAM++), an open-set image tagging model effectively leveraging multi-grained text supervision. Previous approaches (e.g., CLIP) primarily utilize global text supervision paired with images, leading to sub-optimal performance in recognizing multiple individual semantic tags. In contrast, RAM++ seamlessly integrates individual tag supervision with global text supervision, all within a unified alignment framework. This integration not only ensures efficient recognition of predefined tag categories, but also enhances generalization cap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15200","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/2310.15200/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":"2310.15200","created_at":"2026-07-05T07:13:45.365176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15200v2","created_at":"2026-07-05T07:13:45.365176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15200","created_at":"2026-07-05T07:13:45.365176+00:00"},{"alias_kind":"pith_short_12","alias_value":"7B5OBCV5TNQY","created_at":"2026-07-05T07:13:45.365176+00:00"},{"alias_kind":"pith_short_16","alias_value":"7B5OBCV5TNQYTYFZ","created_at":"2026-07-05T07:13:45.365176+00:00"},{"alias_kind":"pith_short_8","alias_value":"7B5OBCV5","created_at":"2026-07-05T07:13:45.365176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY","json":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY.json","graph_json":"https://pith.science/api/pith-number/7B5OBCV5TNQYTYFZWPV7HB4JMY/graph.json","events_json":"https://pith.science/api/pith-number/7B5OBCV5TNQYTYFZWPV7HB4JMY/events.json","paper":"https://pith.science/paper/7B5OBCV5"},"agent_actions":{"view_html":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY","download_json":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY.json","view_paper":"https://pith.science/paper/7B5OBCV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15200&json=true","fetch_graph":"https://pith.science/api/pith-number/7B5OBCV5TNQYTYFZWPV7HB4JMY/graph.json","fetch_events":"https://pith.science/api/pith-number/7B5OBCV5TNQYTYFZWPV7HB4JMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY/action/storage_attestation","attest_author":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY/action/author_attestation","sign_citation":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY/action/citation_signature","submit_replication":"https://pith.science/pith/7B5OBCV5TNQYTYFZWPV7HB4JMY/action/replication_record"}},"created_at":"2026-07-05T07:13:45.365176+00:00","updated_at":"2026-07-05T07:13:45.365176+00:00"}