{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C463RGADLRHZWQDNFDSZM4E22B","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":"635bf3a034cdd213c2167c4e439132c771b64996fb5d0de87d9ab9ee59a78044","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-28T22:07:17Z","title_canon_sha256":"12eaa53751796aca2da11bfe19cf2d42f43ad89bb2bf9362996aa21aaeaaf4e1"},"schema_version":"1.0","source":{"id":"2601.21081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.21081","created_at":"2026-06-19T16:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2601.21081v2","created_at":"2026-06-19T16:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21081","created_at":"2026-06-19T16:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"C463RGADLRHZ","created_at":"2026-06-19T16:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"C463RGADLRHZWQDN","created_at":"2026-06-19T16:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"C463RGAD","created_at":"2026-06-19T16:12:18Z"}],"graph_snapshots":[{"event_id":"sha256:c34708172ac37d083f31a6336a16768335d8a937ffcc850a6f18c2be88ed45bf","target":"graph","created_at":"2026-06-19T16:12:18Z","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/2601.21081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal models for text-to-image generation have achieved strong visual fidelity, yet they remain brittle under compositional structural constraints, notably generative numeracy, attribute binding, and part-level relations. To address these challenges, we propose Shape-of-Thought (SoT), a visual CoT framework for process-supervised progressive shape assembly in the rendered 2D domain, without external engines at inference time. SoT trains a unified multimodal autoregressive model to generate interleaved textual plans and rendered intermediate states, helping the model capture shape-assembly","authors_text":"Haoyue Liu, Junlin Chen, Kun Zeng, Owen Lee, Siyu Zhang, Xiaoying Tang, Yaodong Liang, Yifu Guo, Yu Huo, Yuquan Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-28T22:07:17Z","title":"Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21081","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:ddc65cbe9c86069007a19c89bea9a7497e7d6d223608e64983ad114b9f2165ea","target":"record","created_at":"2026-06-19T16:12:18Z","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":"635bf3a034cdd213c2167c4e439132c771b64996fb5d0de87d9ab9ee59a78044","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-28T22:07:17Z","title_canon_sha256":"12eaa53751796aca2da11bfe19cf2d42f43ad89bb2bf9362996aa21aaeaaf4e1"},"schema_version":"1.0","source":{"id":"2601.21081","kind":"arxiv","version":2}},"canonical_sha256":"173db898035c4f9b406d28e596709ad053595e1492b8fc42edc42c3480366ee4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"173db898035c4f9b406d28e596709ad053595e1492b8fc42edc42c3480366ee4","first_computed_at":"2026-06-19T16:12:18.095950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:18.095950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/5zldexak4PvAIp/B0XPtxF3bAxEsXwAd27fZ3tMRubcg76SDquJVBRPJYhJ7xe/hgVldlvT2FiG1Xu2uUqZDg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:18.096417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.21081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddc65cbe9c86069007a19c89bea9a7497e7d6d223608e64983ad114b9f2165ea","sha256:c34708172ac37d083f31a6336a16768335d8a937ffcc850a6f18c2be88ed45bf"],"state_sha256":"11b4ffd4ee461dee7cb6585b190653da271b7259eb116dd63746da0726e2497f"}