{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CYYK37H7UWKHUPU7MG4J5YABTX","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":"d6fe043b426db740d6fcf30b5b9febcebb1a3cd41b31f668b8d181007c330cc9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T05:30:08Z","title_canon_sha256":"23087d0f96ced5c1a02d99092138fa080d63e873fb5b0dc1e9a261de6c0def9b"},"schema_version":"1.0","source":{"id":"2502.10458","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10458","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10458v1","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10458","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_12","alias_value":"CYYK37H7UWKH","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_16","alias_value":"CYYK37H7UWKHUPU7","created_at":"2026-07-05T10:14:52Z"},{"alias_kind":"pith_short_8","alias_value":"CYYK37H7","created_at":"2026-07-05T10:14:52Z"}],"graph_snapshots":[{"event_id":"sha256:6d95edc208abe5e7b29968de2935e037bed6bee8eaa4e2e899bbcbe6b83c623a","target":"graph","created_at":"2026-07-05T10:14:52Z","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/2502.10458/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents ThinkDiff, a novel alignment paradigm that empowers text-to-image diffusion models with multimodal in-context understanding and reasoning capabilities by integrating the strengths of vision-language models (VLMs). Existing multimodal diffusion finetuning methods largely focus on pixel-level reconstruction rather than in-context reasoning, and are constrained by the complexity and limited availability of reasoning-based datasets. ThinkDiff addresses these challenges by leveraging vision-language training as a proxy task, aligning VLMs with the decoder of an encoder-decoder l","authors_text":"Dan Xu, Guocheng Qian, Hanrong Ye, Kfir Aberman, Kuan-Chieh Wang, Runtao Liu, Sergey Tulyakov, Zhenxing Mi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T05:30:08Z","title":"I Think, Therefore I Diffuse: Enabling Multimodal In-Context Reasoning in Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10458","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":"sha256:9cff100d1973d713e62fba773f1f34515d1ca17f9f9cc2b629d649831a11f3b6","target":"record","created_at":"2026-07-05T10:14:52Z","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":"d6fe043b426db740d6fcf30b5b9febcebb1a3cd41b31f668b8d181007c330cc9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-12T05:30:08Z","title_canon_sha256":"23087d0f96ced5c1a02d99092138fa080d63e873fb5b0dc1e9a261de6c0def9b"},"schema_version":"1.0","source":{"id":"2502.10458","kind":"arxiv","version":1}},"canonical_sha256":"1630adfcffa5947a3e9f61b89ee0019dc62b40a46fe2dc39fa31885cfc05dad2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1630adfcffa5947a3e9f61b89ee0019dc62b40a46fe2dc39fa31885cfc05dad2","first_computed_at":"2026-07-05T10:14:52.972020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:52.972020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DDxY+L65o3v/Mqc7HkcYpBJaYIHZgbIOH7MgAurvUQZh4jbpdoFbXRZHPB7F75Np4MYgsDVN1+DypLjr/RIiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:52.972499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10458","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cff100d1973d713e62fba773f1f34515d1ca17f9f9cc2b629d649831a11f3b6","sha256:6d95edc208abe5e7b29968de2935e037bed6bee8eaa4e2e899bbcbe6b83c623a"],"state_sha256":"2e5d1ccfaf8ffcc2bfb49af569a36714a6e07a3fdac22d4c55637a98d6db91ab"}