{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FXAAHEIZUI7SFD2EEF7WOF77ZD","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":"93ed0343e426dc637203edc8594d687b7f901e9be816d4c2e53aa0d803bee6e3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T19:24:59Z","title_canon_sha256":"befc3821987f3d40a32ccd080fe15b3c0bd6ef9d0665db9dc219e0f946ea7a3f"},"schema_version":"1.0","source":{"id":"2411.02545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02545","created_at":"2026-07-05T09:31:13Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02545v1","created_at":"2026-07-05T09:31:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02545","created_at":"2026-07-05T09:31:13Z"},{"alias_kind":"pith_short_12","alias_value":"FXAAHEIZUI7S","created_at":"2026-07-05T09:31:13Z"},{"alias_kind":"pith_short_16","alias_value":"FXAAHEIZUI7SFD2E","created_at":"2026-07-05T09:31:13Z"},{"alias_kind":"pith_short_8","alias_value":"FXAAHEIZ","created_at":"2026-07-05T09:31:13Z"}],"graph_snapshots":[{"event_id":"sha256:52bc79f8c8ec98a604a38c18f81cc017b128d3e1f08d9602544d1d52c1cde8df","target":"graph","created_at":"2026-07-05T09:31:13Z","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/2411.02545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) models maximize the mutual information between text and visual modalities to learn representations. This makes the nature of the training data a significant factor in the efficacy of CLIP for downstream tasks. However, the lack of compositional diversity in contemporary image-text datasets limits the compositional reasoning ability of CLIP. We show that generating ``hard'' negative captions via in-context learning and synthesizing corresponding negative images with text-to-image generators offers a solution. We introduce a novel contrastive pre-tra","authors_text":"Abhiram Kusumba, Changhoon Kim, Chitta Baral, Maitreya Patel, Sheng Cheng, Tejas Gokhale, Yezhou Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T19:24:59Z","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02545","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":"sha256:74548f08a310b4c875b203e37c971ff5c91bd702029b98e05c291df7f94b4848","target":"record","created_at":"2026-07-05T09:31:13Z","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":"93ed0343e426dc637203edc8594d687b7f901e9be816d4c2e53aa0d803bee6e3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T19:24:59Z","title_canon_sha256":"befc3821987f3d40a32ccd080fe15b3c0bd6ef9d0665db9dc219e0f946ea7a3f"},"schema_version":"1.0","source":{"id":"2411.02545","kind":"arxiv","version":1}},"canonical_sha256":"2dc0039119a23f228f44217f6717ffc8d3668bdf295b3f16563424a31f6c7e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dc0039119a23f228f44217f6717ffc8d3668bdf295b3f16563424a31f6c7e42","first_computed_at":"2026-07-05T09:31:13.754490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:13.754490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5h63d6QEwkIlKkiQcXydlvmeFG/wiFORT5L7vM8Cgx6XAr5qb1hccEFuXX/QfmSqTOfPNdB/D4RpZ3+MwlOTDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:13.754948Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74548f08a310b4c875b203e37c971ff5c91bd702029b98e05c291df7f94b4848","sha256:52bc79f8c8ec98a604a38c18f81cc017b128d3e1f08d9602544d1d52c1cde8df"],"state_sha256":"6a848abb6b552f3e7d2db441cc4b24246c009b78969570503f822f676ef75e66"}