{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4TNKDKGYGDIFOBNTOJ2LMOQLWZ","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":"4d48e55010c0ac15e530b924ff3065ef2e4ccceb5e2575cfea04bcbe4b0e80ee","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T17:59:04Z","title_canon_sha256":"54332e036e7b52dd937b32711b825339825e12df2e7ea1ca5818b98fe8314a47"},"schema_version":"1.0","source":{"id":"2305.20088","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.20088","created_at":"2026-07-05T07:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2305.20088v2","created_at":"2026-07-05T07:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.20088","created_at":"2026-07-05T07:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"4TNKDKGYGDIF","created_at":"2026-07-05T07:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"4TNKDKGYGDIFOBNT","created_at":"2026-07-05T07:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"4TNKDKGY","created_at":"2026-07-05T07:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:cdaba2b28b49fc1e51b3755535b91b3565e657a748a4d90a33e859d26182eb2a","target":"graph","created_at":"2026-07-05T07:06:03Z","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/2305.20088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) stands as one of the most effective and scalable methods for training transferable vision models using paired image and text data. CLIP models are trained using contrastive loss, which typically relies on data augmentations to prevent overfitting and shortcuts. However, in the CLIP training paradigm, data augmentations are exclusively applied to image inputs, while language inputs remain unchanged throughout the entire training process, limiting the exposure of diverse texts to the same image. In this paper, we introduce Language augmented CLIP (L","authors_text":"Dilip Krishnan, Dina Katabi, Lijie Fan, Phillip Isola, Yonglong Tian","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T17:59:04Z","title":"Improving CLIP Training with Language Rewrites"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.20088","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:f60866c9d305964450958a6f0eb0af5b4f5c3c5752534785fa1495d7cd685502","target":"record","created_at":"2026-07-05T07:06:03Z","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":"4d48e55010c0ac15e530b924ff3065ef2e4ccceb5e2575cfea04bcbe4b0e80ee","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-31T17:59:04Z","title_canon_sha256":"54332e036e7b52dd937b32711b825339825e12df2e7ea1ca5818b98fe8314a47"},"schema_version":"1.0","source":{"id":"2305.20088","kind":"arxiv","version":2}},"canonical_sha256":"e4daa1a8d830d05705b37274b63a0bb67a2b08f4fb3cb06e931c56f651ae7a08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4daa1a8d830d05705b37274b63a0bb67a2b08f4fb3cb06e931c56f651ae7a08","first_computed_at":"2026-07-05T07:06:03.531612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:03.531612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SEk+H47mh3RbGVuTIYYkZA6aq86wh+0O46iRL6AgtUIGX/91+rCBP8eOf4vR360fLOxxi+f0If07Zl4zBURCBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:03.532096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.20088","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f60866c9d305964450958a6f0eb0af5b4f5c3c5752534785fa1495d7cd685502","sha256:cdaba2b28b49fc1e51b3755535b91b3565e657a748a4d90a33e859d26182eb2a"],"state_sha256":"438e2af07d348a6e8e1dd5c64351140e393f0a35076e9b77e34db9f63ec62552"}