{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DDLKIDJ4D377RIWVMXODPTXI3V","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":"e63db4df8f308b44dad8120a0121d850aa2c73843361dd5a2c214b76952b8b08","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T17:55:19Z","title_canon_sha256":"9cc170567031008a21e2b26b9be4e3b87f9c090d9eface4706b39a29acea6837"},"schema_version":"1.0","source":{"id":"2310.03734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03734","created_at":"2026-07-05T06:57:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03734v1","created_at":"2026-07-05T06:57:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03734","created_at":"2026-07-05T06:57:37Z"},{"alias_kind":"pith_short_12","alias_value":"DDLKIDJ4D377","created_at":"2026-07-05T06:57:37Z"},{"alias_kind":"pith_short_16","alias_value":"DDLKIDJ4D377RIWV","created_at":"2026-07-05T06:57:37Z"},{"alias_kind":"pith_short_8","alias_value":"DDLKIDJ4","created_at":"2026-07-05T06:57:37Z"}],"graph_snapshots":[{"event_id":"sha256:357e04496d23f3dee70a64fd89623a7e6ae6bb45a659995079aa45a3d9b78abe","target":"graph","created_at":"2026-07-05T06:57:37Z","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/2310.03734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. However, automatically collecting such data (e.g. via large-scale web scraping) leads to low quality and poor image-text correlation, while human annotation is more accurate but requires significant manual effort and expense. We introduce $\\textbf{ITIT}$ ($\\textbf{I}$n$\\textbf{T}$egrating $\\textbf{I}$mage $\\textbf{T}$ext): an innovative training paradigm grounded in the concept of cycle consistency which allows vision-language training on ","authors_text":"Dilip Krishnan, Dina Katabi, Guillaume Lajoie, Han Zhang, Huiwen Chang, Jarred Barber, Sangnie Bhardwaj, Tianhong Li, Yonglong Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T17:55:19Z","title":"Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03734","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:d06282474b51672a4ba94b354d70552b52122736e2c48bbfe5c624735391799e","target":"record","created_at":"2026-07-05T06:57:37Z","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":"e63db4df8f308b44dad8120a0121d850aa2c73843361dd5a2c214b76952b8b08","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-05T17:55:19Z","title_canon_sha256":"9cc170567031008a21e2b26b9be4e3b87f9c090d9eface4706b39a29acea6837"},"schema_version":"1.0","source":{"id":"2310.03734","kind":"arxiv","version":1}},"canonical_sha256":"18d6a40d3c1efff8a2d565dc37cee8dd76558d613b201645d14b88fe6412491b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18d6a40d3c1efff8a2d565dc37cee8dd76558d613b201645d14b88fe6412491b","first_computed_at":"2026-07-05T06:57:37.433143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:37.433143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uvd2BjsiQTFkkGd82ZCznWmgOh4jugNuMlvg2Y9KgD4Zc54ayUIY3ng2lJ/pi1dAhkCrwkaTCXYlTL6s2GwNCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:37.433678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d06282474b51672a4ba94b354d70552b52122736e2c48bbfe5c624735391799e","sha256:357e04496d23f3dee70a64fd89623a7e6ae6bb45a659995079aa45a3d9b78abe"],"state_sha256":"47231643dc99a02552195891d5a51baf1e45e64fe4b0714070ab74988c458293"}