{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4Q2BUKIB7VKUYVI27DUCJEYOTK","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":"b9c3238794487842e1599f5f3595c9314919df767b53240485bca87d4481d614","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T19:55:31Z","title_canon_sha256":"ce818cbda3decb75c35fe26e5422c9c4e0f74b836c2335201eaa6a92ca4a95ab"},"schema_version":"1.0","source":{"id":"2104.08945","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08945","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08945v1","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08945","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_12","alias_value":"4Q2BUKIB7VKU","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_16","alias_value":"4Q2BUKIB7VKUYVI2","created_at":"2026-07-05T02:32:57Z"},{"alias_kind":"pith_short_8","alias_value":"4Q2BUKIB","created_at":"2026-07-05T02:32:57Z"}],"graph_snapshots":[{"event_id":"sha256:63f28e527b8a5a60d0bdefc53c8f403a2202847f9ca013dfed2555c0d6810808","target":"graph","created_at":"2026-07-05T02:32:57Z","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/2104.08945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than supervised \"gold\" labels. Previous works, such as CLIP, use a simple pretraining task of predicting the pairings between images and text captions. CLIP, however, is data hungry and requires more than 400M image text pairs for training. We propose a data-efficient contrastive distillation method that uses soft labels to learn from noisy image-text pairs. ","authors_text":"Bichen Wu, Joseph E. Gonzalez, Peizhao Zhang, Peter Vajda, Ruizhe Cheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T19:55:31Z","title":"Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08945","kind":"arxiv","version":1},"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:e77c1711382383292927bf3c02bc0148ad6ee3346e3e21247bda48d2884f1ab0","target":"record","created_at":"2026-07-05T02:32:57Z","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":"b9c3238794487842e1599f5f3595c9314919df767b53240485bca87d4481d614","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-18T19:55:31Z","title_canon_sha256":"ce818cbda3decb75c35fe26e5422c9c4e0f74b836c2335201eaa6a92ca4a95ab"},"schema_version":"1.0","source":{"id":"2104.08945","kind":"arxiv","version":1}},"canonical_sha256":"e4341a2901fd554c551af8e824930e9ab198902593a144078f8252f6cddf63fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4341a2901fd554c551af8e824930e9ab198902593a144078f8252f6cddf63fb","first_computed_at":"2026-07-05T02:32:57.093476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:57.093476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZNYiHvu7XNQEwe2NnLmugRTHhh7Sgz9wVu9rYcepYnbj2VNd17ZuFJHNWI74Z+FCIpozHP1LR0OG5I50SP8uDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:57.093960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08945","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e77c1711382383292927bf3c02bc0148ad6ee3346e3e21247bda48d2884f1ab0","sha256:63f28e527b8a5a60d0bdefc53c8f403a2202847f9ca013dfed2555c0d6810808"],"state_sha256":"48cef0d251d0f221facaf0939f1928018e330783398ef952a8404d31f9367496"}