{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C463RGADLRHZWQDNFDSZM4E22B","short_pith_number":"pith:C463RGAD","schema_version":"1.0","canonical_sha256":"173db898035c4f9b406d28e596709ad053595e1492b8fc42edc42c3480366ee4","source":{"kind":"arxiv","id":"2601.21081","version":2},"attestation_state":"computed","paper":{"title":"Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyue Liu, Junlin Chen, Kun Zeng, Owen Lee, Siyu Zhang, Xiaoying Tang, Yaodong Liang, Yifu Guo, Yu Huo, Yuquan Lu","submitted_at":"2026-01-28T22:07:17Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.21081","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-28T22:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"12eaa53751796aca2da11bfe19cf2d42f43ad89bb2bf9362996aa21aaeaaf4e1","abstract_canon_sha256":"635bf3a034cdd213c2167c4e439132c771b64996fb5d0de87d9ab9ee59a78044"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:18.096417Z","signature_b64":"/5zldexak4PvAIp/B0XPtxF3bAxEsXwAd27fZ3tMRubcg76SDquJVBRPJYhJ7xe/hgVldlvT2FiG1Xu2uUqZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"173db898035c4f9b406d28e596709ad053595e1492b8fc42edc42c3480366ee4","last_reissued_at":"2026-06-19T16:12:18.095950Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:18.095950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyue Liu, Junlin Chen, Kun Zeng, Owen Lee, Siyu Zhang, Xiaoying Tang, Yaodong Liang, Yifu Guo, Yu Huo, Yuquan Lu","submitted_at":"2026-01-28T22:07:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21081","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.21081/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.21081","created_at":"2026-06-19T16:12:18.096008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21081v2","created_at":"2026-06-19T16:12:18.096008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21081","created_at":"2026-06-19T16:12:18.096008+00:00"},{"alias_kind":"pith_short_12","alias_value":"C463RGADLRHZ","created_at":"2026-06-19T16:12:18.096008+00:00"},{"alias_kind":"pith_short_16","alias_value":"C463RGADLRHZWQDN","created_at":"2026-06-19T16:12:18.096008+00:00"},{"alias_kind":"pith_short_8","alias_value":"C463RGAD","created_at":"2026-06-19T16:12:18.096008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B","json":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B.json","graph_json":"https://pith.science/api/pith-number/C463RGADLRHZWQDNFDSZM4E22B/graph.json","events_json":"https://pith.science/api/pith-number/C463RGADLRHZWQDNFDSZM4E22B/events.json","paper":"https://pith.science/paper/C463RGAD"},"agent_actions":{"view_html":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B","download_json":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B.json","view_paper":"https://pith.science/paper/C463RGAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21081&json=true","fetch_graph":"https://pith.science/api/pith-number/C463RGADLRHZWQDNFDSZM4E22B/graph.json","fetch_events":"https://pith.science/api/pith-number/C463RGADLRHZWQDNFDSZM4E22B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B/action/storage_attestation","attest_author":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B/action/author_attestation","sign_citation":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B/action/citation_signature","submit_replication":"https://pith.science/pith/C463RGADLRHZWQDNFDSZM4E22B/action/replication_record"}},"created_at":"2026-06-19T16:12:18.096008+00:00","updated_at":"2026-06-19T16:12:18.096008+00:00"}