{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VMUKFKUH75VLCCHE253MGJ6HCU","short_pith_number":"pith:VMUKFKUH","schema_version":"1.0","canonical_sha256":"ab28a2aa87ff6ab108e4d776c327c715063228fe3d039edc3e5c3301ee62d2c7","source":{"kind":"arxiv","id":"2112.07133","version":2},"attestation_state":"computed","paper":{"title":"CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aman Shrivastava, Nikhil Naik, Ramprasaath R. Selvaraju, Vicente Ordonez","submitted_at":"2021-12-14T03:08:37Z","abstract_excerpt":"We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample pair for every positive image-text sample during the optimization of its contrastive learning objective. We accomplish this by taking advantage of an information efficient lower-bound to maximize the mutual information between the two input modalities. This allows CLIP-Lite to be trained with significantly reduced amounts of data and batch sizes while obtaini"},"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":"2112.07133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T03:08:37Z","cross_cats_sorted":[],"title_canon_sha256":"ff6ed2c04853a52ee0656252679c375762d35f86a3243c1c863c621d448a78a3","abstract_canon_sha256":"86d5c3a071a3a53d5171f158ca685362df71e405fa02f1ddbd76c66f99cbbea8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:03.967200Z","signature_b64":"IQSv0sboUYXrfw4iTZ/9YPSqmq0udjkq3C2PJcDHl3kC7WgXXGnLboXRJZlKytzhsITEtWKAa9vU6Q73jcuGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab28a2aa87ff6ab108e4d776c327c715063228fe3d039edc3e5c3301ee62d2c7","last_reissued_at":"2026-07-05T06:09:03.966728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:03.966728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aman Shrivastava, Nikhil Naik, Ramprasaath R. Selvaraju, Vicente Ordonez","submitted_at":"2021-12-14T03:08:37Z","abstract_excerpt":"We propose CLIP-Lite, an information efficient method for visual representation learning by feature alignment with textual annotations. Compared to the previously proposed CLIP model, CLIP-Lite requires only one negative image-text sample pair for every positive image-text sample during the optimization of its contrastive learning objective. We accomplish this by taking advantage of an information efficient lower-bound to maximize the mutual information between the two input modalities. This allows CLIP-Lite to be trained with significantly reduced amounts of data and batch sizes while obtaini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07133","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/2112.07133/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":"2112.07133","created_at":"2026-07-05T06:09:03.966786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07133v2","created_at":"2026-07-05T06:09:03.966786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07133","created_at":"2026-07-05T06:09:03.966786+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMUKFKUH75VL","created_at":"2026-07-05T06:09:03.966786+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMUKFKUH75VLCCHE","created_at":"2026-07-05T06:09:03.966786+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMUKFKUH","created_at":"2026-07-05T06:09:03.966786+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/VMUKFKUH75VLCCHE253MGJ6HCU","json":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU.json","graph_json":"https://pith.science/api/pith-number/VMUKFKUH75VLCCHE253MGJ6HCU/graph.json","events_json":"https://pith.science/api/pith-number/VMUKFKUH75VLCCHE253MGJ6HCU/events.json","paper":"https://pith.science/paper/VMUKFKUH"},"agent_actions":{"view_html":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU","download_json":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU.json","view_paper":"https://pith.science/paper/VMUKFKUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07133&json=true","fetch_graph":"https://pith.science/api/pith-number/VMUKFKUH75VLCCHE253MGJ6HCU/graph.json","fetch_events":"https://pith.science/api/pith-number/VMUKFKUH75VLCCHE253MGJ6HCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU/action/storage_attestation","attest_author":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU/action/author_attestation","sign_citation":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU/action/citation_signature","submit_replication":"https://pith.science/pith/VMUKFKUH75VLCCHE253MGJ6HCU/action/replication_record"}},"created_at":"2026-07-05T06:09:03.966786+00:00","updated_at":"2026-07-05T06:09:03.966786+00:00"}