{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IOO7NFL3H4NU7DPZSL4EV7VX6U","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":"2c34cad7840738a6ac1010a22fc49cf06ac65cc0ce49772a1653bdd37de6f491","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T06:03:05Z","title_canon_sha256":"8d297bd3ed98bcea83857d4367cf672559a774084259f9287b50f21e9452811b"},"schema_version":"1.0","source":{"id":"2412.12571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12571","created_at":"2026-07-05T09:50:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12571v1","created_at":"2026-07-05T09:50:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12571","created_at":"2026-07-05T09:50:17Z"},{"alias_kind":"pith_short_12","alias_value":"IOO7NFL3H4NU","created_at":"2026-07-05T09:50:17Z"},{"alias_kind":"pith_short_16","alias_value":"IOO7NFL3H4NU7DPZ","created_at":"2026-07-05T09:50:17Z"},{"alias_kind":"pith_short_8","alias_value":"IOO7NFL3","created_at":"2026-07-05T09:50:17Z"}],"graph_snapshots":[{"event_id":"sha256:0889fa9abc390802263ff56751c0ebed57a4f831ebb0602fdb22d6d509ea2fb2","target":"graph","created_at":"2026-07-05T09:50:17Z","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/2412.12571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research arXiv:2410.15027 arXiv:2410.23775 has highlighted the inherent in-context generation capabilities of pretrained diffusion transformers (DiTs), enabling them to seamlessly adapt to diverse visual tasks with minimal or no architectural modifications. These capabilities are unlocked by concatenating self-attention tokens across multiple input and target images, combined with grouped and masked generation pipelines. Building upon this foundation, we present ChatDiT, a zero-shot, general-purpose, and interactive visual generation framework that leverages pretrained diffusion transfo","authors_text":"Chen Liang, Han Zhang, Huanzhang Dou, Jingren Zhou, Lianghua Huang, Tong Shen, Wei Wang, Yu Liu, Yupeng Shi, Zhi-Fan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T06:03:05Z","title":"ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12571","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":"sha256:2ff75c9fa42c9735adfe42830f286d3a7e6800209ea445d5d39fc07716cd224c","target":"record","created_at":"2026-07-05T09:50:17Z","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":"2c34cad7840738a6ac1010a22fc49cf06ac65cc0ce49772a1653bdd37de6f491","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T06:03:05Z","title_canon_sha256":"8d297bd3ed98bcea83857d4367cf672559a774084259f9287b50f21e9452811b"},"schema_version":"1.0","source":{"id":"2412.12571","kind":"arxiv","version":1}},"canonical_sha256":"439df6957b3f1b4f8df992f84afeb7f514473b4ca980996254487e012be31b91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"439df6957b3f1b4f8df992f84afeb7f514473b4ca980996254487e012be31b91","first_computed_at":"2026-07-05T09:50:17.171781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:17.171781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ePq6X2wwBd7MclP9XIEnzFGQmOQ8xXxwKZdPs+EFCQUUDafSNNU5I5l+L+A9U/6Q3/4wL988ql696YA8w1b6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:17.172214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ff75c9fa42c9735adfe42830f286d3a7e6800209ea445d5d39fc07716cd224c","sha256:0889fa9abc390802263ff56751c0ebed57a4f831ebb0602fdb22d6d509ea2fb2"],"state_sha256":"0e337d61c3822bb525a11dfec1ed462e955b83c20dad8a334a4fd5e445f5250a"}