{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A5C6JEI7JSOZFKMIKRAL4QADRC","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":"32fb8343f7b43ce3d729bb992f1330bed5d44ec8dc0036a380a2fc8d430f4069","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:59Z","title_canon_sha256":"c084fade014dc7e25484b5522c995e944703ac57d3abf0f5bf0b17a6057bda72"},"schema_version":"1.0","source":{"id":"2503.10639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10639","created_at":"2026-07-05T10:30:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10639v1","created_at":"2026-07-05T10:30:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10639","created_at":"2026-07-05T10:30:49Z"},{"alias_kind":"pith_short_12","alias_value":"A5C6JEI7JSOZ","created_at":"2026-07-05T10:30:49Z"},{"alias_kind":"pith_short_16","alias_value":"A5C6JEI7JSOZFKMI","created_at":"2026-07-05T10:30:49Z"},{"alias_kind":"pith_short_8","alias_value":"A5C6JEI7","created_at":"2026-07-05T10:30:49Z"}],"graph_snapshots":[{"event_id":"sha256:663e77b2004d27a457823ae2d61d55227da6930ebad627b68054f732082ce676","target":"graph","created_at":"2026-07-05T10:30:49Z","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/2503.10639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current image generation and editing methods primarily process textual prompts as direct inputs without reasoning about visual composition and explicit operations. We present Generation Chain-of-Thought (GoT), a novel paradigm that enables generation and editing through an explicit language reasoning process before outputting images. This approach transforms conventional text-to-image generation and editing into a reasoning-guided framework that analyzes semantic relationships and spatial arrangements. We define the formulation of GoT and construct large-scale GoT datasets containing over 9M s","authors_text":"Chengqi Duan, Hao Li, Hao Tian, Hongsheng Li, Jifeng Dai, Kun Wang, LinJiang Huang, Rongyao Fang, Rui Zhao, Shilin Yan, Xihui Liu, Xingyu Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:59Z","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10639","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:f9dd2cce12cdf036a8660e06f4cee9897b189c26ac98e26ce5ca85fd7a4d5c84","target":"record","created_at":"2026-07-05T10:30:49Z","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":"32fb8343f7b43ce3d729bb992f1330bed5d44ec8dc0036a380a2fc8d430f4069","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-13T17:59:59Z","title_canon_sha256":"c084fade014dc7e25484b5522c995e944703ac57d3abf0f5bf0b17a6057bda72"},"schema_version":"1.0","source":{"id":"2503.10639","kind":"arxiv","version":1}},"canonical_sha256":"0745e4911f4c9d92a9885440be400388a48dff43860d82004d9457b8783a68e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0745e4911f4c9d92a9885440be400388a48dff43860d82004d9457b8783a68e9","first_computed_at":"2026-07-05T10:30:49.375680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:49.375680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"plAJM7LQ+NrjfqbuCtzEq7lyycONarYsMP+Bd8vmZAlWlxvSdThRNvJCWvfejLGuOM+byCNZp/Ur/vboeV4UCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:49.376208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9dd2cce12cdf036a8660e06f4cee9897b189c26ac98e26ce5ca85fd7a4d5c84","sha256:663e77b2004d27a457823ae2d61d55227da6930ebad627b68054f732082ce676"],"state_sha256":"77ed895a3692de2d37481217558814b5e4e33cc2b37eaf6b95814eed962431c0"}