{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VMUKFKUH75VLCCHE253MGJ6HCU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"86d5c3a071a3a53d5171f158ca685362df71e405fa02f1ddbd76c66f99cbbea8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T03:08:37Z","title_canon_sha256":"ff6ed2c04853a52ee0656252679c375762d35f86a3243c1c863c621d448a78a3"},"schema_version":"1.0","source":{"id":"2112.07133","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07133","created_at":"2026-07-05T06:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07133v2","created_at":"2026-07-05T06:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07133","created_at":"2026-07-05T06:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"VMUKFKUH75VL","created_at":"2026-07-05T06:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"VMUKFKUH75VLCCHE","created_at":"2026-07-05T06:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"VMUKFKUH","created_at":"2026-07-05T06:09:03Z"}],"graph_snapshots":[{"event_id":"sha256:0a694df492278917eaf8c371ccb68364f0c54edfbc26a89e2f2161f9077a3137","target":"graph","created_at":"2026-07-05T06:09:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.07133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aman Shrivastava, Nikhil Naik, Ramprasaath R. Selvaraju, Vicente Ordonez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T03:08:37Z","title":"CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07133","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b31b28182a6cf2307503714e46c3da8c8b796c25a7067281c095635b3dcd213","target":"record","created_at":"2026-07-05T06:09:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"86d5c3a071a3a53d5171f158ca685362df71e405fa02f1ddbd76c66f99cbbea8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T03:08:37Z","title_canon_sha256":"ff6ed2c04853a52ee0656252679c375762d35f86a3243c1c863c621d448a78a3"},"schema_version":"1.0","source":{"id":"2112.07133","kind":"arxiv","version":2}},"canonical_sha256":"ab28a2aa87ff6ab108e4d776c327c715063228fe3d039edc3e5c3301ee62d2c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab28a2aa87ff6ab108e4d776c327c715063228fe3d039edc3e5c3301ee62d2c7","first_computed_at":"2026-07-05T06:09:03.966728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:09:03.966728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQSv0sboUYXrfw4iTZ/9YPSqmq0udjkq3C2PJcDHl3kC7WgXXGnLboXRJZlKytzhsITEtWKAa9vU6Q73jcuGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:09:03.967200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07133","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b31b28182a6cf2307503714e46c3da8c8b796c25a7067281c095635b3dcd213","sha256:0a694df492278917eaf8c371ccb68364f0c54edfbc26a89e2f2161f9077a3137"],"state_sha256":"e1969fc555007631bb7ea2c5973769438d9f89a3fcc3e4c6de1b85f6452b168c"}