{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LZJ66MXMUQZO7QQ4MO7NRCDCA3","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":"163fa66505115fd953bea048e2ed1bda789bc4ad180644f37fc8fb00b01fb1bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T07:37:23Z","title_canon_sha256":"7dcf529253a54e51a3bae1b19b9c8c7869a799160eb42e39c3c5e62dcb24ef22"},"schema_version":"1.0","source":{"id":"2408.10605","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10605","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10605v5","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10605","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_12","alias_value":"LZJ66MXMUQZO","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_16","alias_value":"LZJ66MXMUQZO7QQ4","created_at":"2026-07-05T09:49:09Z"},{"alias_kind":"pith_short_8","alias_value":"LZJ66MXM","created_at":"2026-07-05T09:49:09Z"}],"graph_snapshots":[{"event_id":"sha256:594de9d8a69450172ed0a1901ddaabc4dc488d0c7eff74039451af50ccf35b5a","target":"graph","created_at":"2026-07-05T09:49:09Z","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/2408.10605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES addresses this challenging task by developing a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By m","authors_text":"Kunchang Li, Shaobin Zhuang, Yali Wang, Yanbo Ding, Yu Qiao, Zhengrong Yue","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T07:37:23Z","title":"MUSES: 3D-Controllable Image Generation via Multi-Modal Agent Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10605","kind":"arxiv","version":5},"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:add53b269eee3638aaf60f03f99df51c35866bf1fb99e5bdd477949119c0fe62","target":"record","created_at":"2026-07-05T09:49:09Z","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":"163fa66505115fd953bea048e2ed1bda789bc4ad180644f37fc8fb00b01fb1bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-20T07:37:23Z","title_canon_sha256":"7dcf529253a54e51a3bae1b19b9c8c7869a799160eb42e39c3c5e62dcb24ef22"},"schema_version":"1.0","source":{"id":"2408.10605","kind":"arxiv","version":5}},"canonical_sha256":"5e53ef32eca432efc21c63bed8886206cb00ce087918d69258f097c4bc8b4f95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e53ef32eca432efc21c63bed8886206cb00ce087918d69258f097c4bc8b4f95","first_computed_at":"2026-07-05T09:49:09.105504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:09.105504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HxjbA6hhyUS+oNUil2PlLnzsYi9lBol1NhE/S3D8YHX2UBIz3PJFgMPCxugS6+elzmut/4rXfGAbi9UZt1P5CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:09.105964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10605","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:add53b269eee3638aaf60f03f99df51c35866bf1fb99e5bdd477949119c0fe62","sha256:594de9d8a69450172ed0a1901ddaabc4dc488d0c7eff74039451af50ccf35b5a"],"state_sha256":"de7e064c58968f78739bc2f2c87fa6b0731ccab0b0e208f92151b54af991e788"}