{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6PNAOWC7OR6QWOU2DFUI6M5K3W","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":"0dda763031da337cd87e9e6c77ee05dbaa74e5b336385327843fe65de533ee35","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T23:22:47Z","title_canon_sha256":"6c2d173eabc2045d402c21c056fac02edc5126f9b4a8fe1e11e0bee325c6c534"},"schema_version":"1.0","source":{"id":"2312.12661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12661","created_at":"2026-07-05T07:26:24Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12661v1","created_at":"2026-07-05T07:26:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12661","created_at":"2026-07-05T07:26:24Z"},{"alias_kind":"pith_short_12","alias_value":"6PNAOWC7OR6Q","created_at":"2026-07-05T07:26:24Z"},{"alias_kind":"pith_short_16","alias_value":"6PNAOWC7OR6QWOU2","created_at":"2026-07-05T07:26:24Z"},{"alias_kind":"pith_short_8","alias_value":"6PNAOWC7","created_at":"2026-07-05T07:26:24Z"}],"graph_snapshots":[{"event_id":"sha256:661520ec5460a9fb6212713e672ac3c79e8fa1c3c00f2e714521dda900f4a6e8","target":"graph","created_at":"2026-07-05T07:26:24Z","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/2312.12661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining has emerged as a prominent approach for training vision and text encoders with uncurated image-text pairs from the web. To enhance data-efficiency, recent efforts have introduced additional supervision terms that involve random-augmented views of the image. However, since the image augmentation process is unaware of its text counterpart, this procedure could cause various degrees of image-text misalignments during training. Prior methods either disregarded this discrepancy or introduced external models to mitigate the impact of misalignments during traini","authors_text":"Bumsoo Kim, Jinhyung Kim, Seung Hwan Kim, Yeonsik Jo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T23:22:47Z","title":"Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12661","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":"sha256:65494ffe435d2401fcecf471c3b940d588c7ef8fe782548900f50b62c845322c","target":"record","created_at":"2026-07-05T07:26:24Z","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":"0dda763031da337cd87e9e6c77ee05dbaa74e5b336385327843fe65de533ee35","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-19T23:22:47Z","title_canon_sha256":"6c2d173eabc2045d402c21c056fac02edc5126f9b4a8fe1e11e0bee325c6c534"},"schema_version":"1.0","source":{"id":"2312.12661","kind":"arxiv","version":1}},"canonical_sha256":"f3da07585f747d0b3a9a19688f33aaddb0cf0e70888df4d6bc53d87f74ad8283","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3da07585f747d0b3a9a19688f33aaddb0cf0e70888df4d6bc53d87f74ad8283","first_computed_at":"2026-07-05T07:26:24.669738Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:24.669738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"74MXC7j3M1ugklnFWn6+mspTcReGcuMb0fK9uW8Rgf/BOo+ldzzwPpvPqx3LljfmhVDY8tn7d5xLoeDH+BsBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:24.670219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65494ffe435d2401fcecf471c3b940d588c7ef8fe782548900f50b62c845322c","sha256:661520ec5460a9fb6212713e672ac3c79e8fa1c3c00f2e714521dda900f4a6e8"],"state_sha256":"714a284724d4093dc64e3c6b577b2d4a4f2f60845bec39b21f9b083f606b66e6"}