{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z3WAOVIW5JQBJEMHST6E2V5VTZ","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":"ab93f4276786e9d3702f518d47951ec97fa934e99c4ff3bd090710a09cad5086","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:52:40Z","title_canon_sha256":"26cc0ec4c2326f662f1c43320ac202e6244b883bfd520ec1eb0e1fc4b408e371"},"schema_version":"1.0","source":{"id":"2412.03558","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03558","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03558v3","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03558","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"Z3WAOVIW5JQB","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"pith_short_16","alias_value":"Z3WAOVIW5JQBJEMH","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"pith_short_8","alias_value":"Z3WAOVIW","created_at":"2026-07-05T11:38:25Z"}],"graph_snapshots":[{"event_id":"sha256:9ed94de706e6f4f72865b5a0237c182ee08aa8202f85227a763ca1bc1ce04e06","target":"graph","created_at":"2026-07-05T11:38:25Z","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/2412.03558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage object-by-object generation, MIDI extends pre-trained image-to-3D object generation models to multi-instance diffusion models, enabling the simultaneous generation of multiple 3D instances with accurate spatial relationships and high generalizability. At its core, MIDI incorporates a novel multi-instance attention mechanism, that effectively captures inter-object interacti","authors_text":"Ding Liang, Lu Sheng, Xihui Liu, Xingqiao An, Yangguang Li, Yan-Pei Cao, Yuan-Chen Guo, Yunhan Yang, Zehuan Huang, Zi-Xin Zou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:52:40Z","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03558","kind":"arxiv","version":3},"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:b36d8a19eb2a45faf3cf518a49bc2c51184b8ab7bb5a8c66ab9f460cdc01af9e","target":"record","created_at":"2026-07-05T11:38:25Z","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":"ab93f4276786e9d3702f518d47951ec97fa934e99c4ff3bd090710a09cad5086","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-04T18:52:40Z","title_canon_sha256":"26cc0ec4c2326f662f1c43320ac202e6244b883bfd520ec1eb0e1fc4b408e371"},"schema_version":"1.0","source":{"id":"2412.03558","kind":"arxiv","version":3}},"canonical_sha256":"ceec075516ea6014918794fc4d57b59e411ed082074fb01a4a9ebafce7e8584d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceec075516ea6014918794fc4d57b59e411ed082074fb01a4a9ebafce7e8584d","first_computed_at":"2026-07-05T11:38:25.655669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:25.655669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wv7M38O5Z1o2mXC1TN1bI/TvBlDGE8tJ6Qkd1mkd74J5u6bFBAtyjysdoE6N0lY/MBeA53cDtAUrywBBYqnyDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:25.656380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03558","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b36d8a19eb2a45faf3cf518a49bc2c51184b8ab7bb5a8c66ab9f460cdc01af9e","sha256:9ed94de706e6f4f72865b5a0237c182ee08aa8202f85227a763ca1bc1ce04e06"],"state_sha256":"6b110c2a3fa9395a3566b811ff1d2e5d4e3811ed74fc748b2fcff3f1439574ca"}