{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EXP2CIEKR5HXSPSBY2NEK2VOIY","short_pith_number":"pith:EXP2CIEK","schema_version":"1.0","canonical_sha256":"25dfa1208a8f4f793e41c69a456aae46047a07be5457dca5e3a31bc43b328c94","source":{"kind":"arxiv","id":"2111.14745","version":1},"attestation_state":"computed","paper":{"title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jiasen Lu, Jing Shao, Mengmeng Wang, Peng Gao, Shijie Geng, Teli Ma, Yu Qiao","submitted_at":"2021-11-29T17:49:24Z","abstract_excerpt":"The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to address the problem. However, they still train models with a finite set of predefined labels, limiting their supervision information and restricting their transferability to novel instances. Recent advances in large-scale contrastive visual-language pretraining shed light on a new pathway for visual recognition. With open-vocabulary supervisions, pretrained c"},"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":"2111.14745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T17:49:24Z","cross_cats_sorted":[],"title_canon_sha256":"f42942f21cd9513fd118e58299d3db0553bed678276f624fb30004c627ffb172","abstract_canon_sha256":"ee0ec4010614f9f1a68cf8035663faad4fe8a0dce5156054462e5c0c1e93c82c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:55.070108Z","signature_b64":"761UA+c/DuS2O1iCH3pvSOi/YPACw1sHcdAP1ELN+5PrBvu5lBvAzUL0pXpR/F2vPrg/r/hXGoxuhnnrblrgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25dfa1208a8f4f793e41c69a456aae46047a07be5457dca5e3a31bc43b328c94","last_reissued_at":"2026-07-05T03:35:55.069633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:55.069633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Long-Tailed Recognition Baseline via Vision-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongsheng Li, Jiasen Lu, Jing Shao, Mengmeng Wang, Peng Gao, Shijie Geng, Teli Ma, Yu Qiao","submitted_at":"2021-11-29T17:49:24Z","abstract_excerpt":"The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Existing approaches either perform class re-balancing strategies or directly improve network modules to address the problem. However, they still train models with a finite set of predefined labels, limiting their supervision information and restricting their transferability to novel instances. Recent advances in large-scale contrastive visual-language pretraining shed light on a new pathway for visual recognition. With open-vocabulary supervisions, pretrained c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14745","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/2111.14745/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":"2111.14745","created_at":"2026-07-05T03:35:55.069685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.14745v1","created_at":"2026-07-05T03:35:55.069685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14745","created_at":"2026-07-05T03:35:55.069685+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXP2CIEKR5HX","created_at":"2026-07-05T03:35:55.069685+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXP2CIEKR5HXSPSB","created_at":"2026-07-05T03:35:55.069685+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXP2CIEK","created_at":"2026-07-05T03:35:55.069685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01309","citing_title":"CUE: Concept-Aware Multi-Label Expansion to Mitigate Concept Confusion in Long-Tailed Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16884","citing_title":"Bias-constrained multimodal intelligence for equitable and reliable clinical AI","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY","json":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY.json","graph_json":"https://pith.science/api/pith-number/EXP2CIEKR5HXSPSBY2NEK2VOIY/graph.json","events_json":"https://pith.science/api/pith-number/EXP2CIEKR5HXSPSBY2NEK2VOIY/events.json","paper":"https://pith.science/paper/EXP2CIEK"},"agent_actions":{"view_html":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY","download_json":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY.json","view_paper":"https://pith.science/paper/EXP2CIEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.14745&json=true","fetch_graph":"https://pith.science/api/pith-number/EXP2CIEKR5HXSPSBY2NEK2VOIY/graph.json","fetch_events":"https://pith.science/api/pith-number/EXP2CIEKR5HXSPSBY2NEK2VOIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY/action/storage_attestation","attest_author":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY/action/author_attestation","sign_citation":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY/action/citation_signature","submit_replication":"https://pith.science/pith/EXP2CIEKR5HXSPSBY2NEK2VOIY/action/replication_record"}},"created_at":"2026-07-05T03:35:55.069685+00:00","updated_at":"2026-07-05T03:35:55.069685+00:00"}