{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3OSHVB7Q7B3ZG4HXF5IPGG3QKZ","short_pith_number":"pith:3OSHVB7Q","schema_version":"1.0","canonical_sha256":"dba47a87f0f8779370f72f50f31b70565f8cb4b3ea7ea4234bc931ca415e0f5b","source":{"kind":"arxiv","id":"2411.03313","version":2},"attestation_state":"computed","paper":{"title":"Classification Done Right for Vision-Language Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Haoqi Fan, Jiashi Feng, Qinghao Ye, Zilong Huang","submitted_at":"2024-11-05T18:58:15Z","abstract_excerpt":"We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes tokenized raw text as supervised classification labels, without the need for additional text filtering or selection. Due to the absence of the text encoding as contrastive target, SuperClass does not require a text encoder and does not need to maintain a large batch size as CLIP does. SuperClass demonstrated superior performance on various downstream tasks, including classic comp"},"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":"2411.03313","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-05T18:58:15Z","cross_cats_sorted":[],"title_canon_sha256":"883c981343bfa80125c873001504bf1cbfbf48c3f581e0a6d63442f631a84cb9","abstract_canon_sha256":"b0e7a0e0adf2830be8009273b059ebc1a6f6562b8056d34224d1a0c30a312a99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:52.094927Z","signature_b64":"Ti6v6k24h7xTvVx8I+DgVK4OncilrTnHh2jFZGvd1NI44dRRL/qpyk0llRyf+sPc2CjaMuEQ4Bj791Weum/BDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dba47a87f0f8779370f72f50f31b70565f8cb4b3ea7ea4234bc931ca415e0f5b","last_reissued_at":"2026-07-05T09:31:52.094427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:52.094427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Classification Done Right for Vision-Language Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Haoqi Fan, Jiashi Feng, Qinghao Ye, Zilong Huang","submitted_at":"2024-11-05T18:58:15Z","abstract_excerpt":"We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes tokenized raw text as supervised classification labels, without the need for additional text filtering or selection. Due to the absence of the text encoding as contrastive target, SuperClass does not require a text encoder and does not need to maintain a large batch size as CLIP does. SuperClass demonstrated superior performance on various downstream tasks, including classic comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03313","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/2411.03313/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":"2411.03313","created_at":"2026-07-05T09:31:52.094497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03313v2","created_at":"2026-07-05T09:31:52.094497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03313","created_at":"2026-07-05T09:31:52.094497+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OSHVB7Q7B3Z","created_at":"2026-07-05T09:31:52.094497+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OSHVB7Q7B3ZG4HX","created_at":"2026-07-05T09:31:52.094497+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OSHVB7Q","created_at":"2026-07-05T09:31:52.094497+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/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ","json":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ.json","graph_json":"https://pith.science/api/pith-number/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/graph.json","events_json":"https://pith.science/api/pith-number/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/events.json","paper":"https://pith.science/paper/3OSHVB7Q"},"agent_actions":{"view_html":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ","download_json":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ.json","view_paper":"https://pith.science/paper/3OSHVB7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03313&json=true","fetch_graph":"https://pith.science/api/pith-number/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/action/storage_attestation","attest_author":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/action/author_attestation","sign_citation":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/action/citation_signature","submit_replication":"https://pith.science/pith/3OSHVB7Q7B3ZG4HXF5IPGG3QKZ/action/replication_record"}},"created_at":"2026-07-05T09:31:52.094497+00:00","updated_at":"2026-07-05T09:31:52.094497+00:00"}