{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RFI5KKZZZ7L3WJ4APACYF2Z4SY","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":"385672dc0784ac59116781e12db510f4d6296ec473c05f621bd5d2be80ad53d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-03T06:54:19Z","title_canon_sha256":"2b22dbed0fc1c07722929ab60c9b784aa12c9652c30ca2126d99158e8ec5a772"},"schema_version":"1.0","source":{"id":"2603.02667","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.02667","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2603.02667v2","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.02667","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"RFI5KKZZZ7L3","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"RFI5KKZZZ7L3WJ4A","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"RFI5KKZZ","created_at":"2026-05-20T00:03:07Z"}],"graph_snapshots":[{"event_id":"sha256:e2d6bd93f30c63bf554473c56c3a034760778c479a69288c8db3202a51e9aa47","target":"graph","created_at":"2026-05-20T00:03:07Z","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/2603.02667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unifying text-image contrastive learning and text-to-image (T2I) generation in a single end-to-end model is challenging because the two objectives demand opposing masking regimes: contrastive alignment needs near-complete visible tokens, while masked generative modeling needs heavy corruption. We introduce DREAM, a unified framework that resolves this conflict through Masking Warmup, a schedule that shifts the center of the masking distribution over training, so low and high masking ratios coexist at every step. This co-exposure lets a single jointly-trained encoder serve both objectives. The ","authors_text":"Aashu Singh, Chao Li, Dina Katabi, Hong-You Chen, Jianpeng Cheng, Jun Xiao, Sai Vidyaranya Nuthalapati, Satya Narayan Shukla, Shlok Kumar Mishra, Tianhong Li, Xiangjun Fan, Yonghuan Yang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-03T06:54:19Z","title":"Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.02667","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":"sha256:8081395f2a7f500b19d0594ccf2972ec42b594ed3b28a7bda739ca65c55ca7b6","target":"record","created_at":"2026-05-20T00:03:07Z","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":"385672dc0784ac59116781e12db510f4d6296ec473c05f621bd5d2be80ad53d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-03T06:54:19Z","title_canon_sha256":"2b22dbed0fc1c07722929ab60c9b784aa12c9652c30ca2126d99158e8ec5a772"},"schema_version":"1.0","source":{"id":"2603.02667","kind":"arxiv","version":2}},"canonical_sha256":"8951d52b39cfd7bb2780780582eb3c9634d88aea3df6e70cbd5889f7b2fc9250","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8951d52b39cfd7bb2780780582eb3c9634d88aea3df6e70cbd5889f7b2fc9250","first_computed_at":"2026-05-20T00:03:07.667566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:07.667566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CZtUj1TNZcGTdG4ikeaHMHApZVpeV+VCn0yCi9tyg7lTjcIuxntPZnN1cGGNHTyouUw1uWw6O6m7GGVyxbvECQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:07.668409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.02667","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8081395f2a7f500b19d0594ccf2972ec42b594ed3b28a7bda739ca65c55ca7b6","sha256:e2d6bd93f30c63bf554473c56c3a034760778c479a69288c8db3202a51e9aa47"],"state_sha256":"3d7e56f988a79d48eb9a77ea3eee650a5dce08cf4ea55f9867c0bee8a9aadaef"}