{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KMZ5WDPEVUJUDIDRQHOJUDEVO3","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":"a8f63415ff5ff5db01a8d8233cb76b6d452f88802283fa56620f617398d3c335","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:23:13Z","title_canon_sha256":"e118827b93088576ed59caebd01c394fd93361ee1254412a71b29656acc90813"},"schema_version":"1.0","source":{"id":"2410.10745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10745","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10745v1","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10745","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"pith_short_12","alias_value":"KMZ5WDPEVUJU","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"pith_short_16","alias_value":"KMZ5WDPEVUJUDIDR","created_at":"2026-07-05T09:20:20Z"},{"alias_kind":"pith_short_8","alias_value":"KMZ5WDPE","created_at":"2026-07-05T09:20:20Z"}],"graph_snapshots":[{"event_id":"sha256:dd6929c9101c0fa61a251fd322bb28b65d33e899b5e79165b265ad6a1f55b8b8","target":"graph","created_at":"2026-07-05T09:20:20Z","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/2410.10745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce FlexGen, a flexible framework designed to generate controllable and consistent multi-view images, conditioned on a single-view image, or a text prompt, or both. FlexGen tackles the challenges of controllable multi-view synthesis through additional conditioning on 3D-aware text annotations. We utilize the strong reasoning capabilities of GPT-4V to generate 3D-aware text annotations. By analyzing four orthogonal views of an object arranged as tiled multi-view images, GPT-4V can produce text annotations that include 3D-aware information with spatial relationship. By int","authors_text":"HanFeng Zhao, Jiantao Lin, Jiawei Feng, Lie Xu, Shunsi Zhang, Wenhang Ge, Xinli Xu, Ying-Cong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:23:13Z","title":"FlexGen: Flexible Multi-View Generation from Text and Image Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10745","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":"sha256:42cce52c541a24397d06f855a5242804fd84e2f602ce9995ab49a0f7548e5bc9","target":"record","created_at":"2026-07-05T09:20:20Z","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":"a8f63415ff5ff5db01a8d8233cb76b6d452f88802283fa56620f617398d3c335","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T17:23:13Z","title_canon_sha256":"e118827b93088576ed59caebd01c394fd93361ee1254412a71b29656acc90813"},"schema_version":"1.0","source":{"id":"2410.10745","kind":"arxiv","version":1}},"canonical_sha256":"5333db0de4ad1341a07181dc9a0c9576e70144c127b616f84b3b378e737afbb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5333db0de4ad1341a07181dc9a0c9576e70144c127b616f84b3b378e737afbb4","first_computed_at":"2026-07-05T09:20:20.489561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:20:20.489561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XtRn2UBon6eJ4oYNAgp1I1j2/aIFPj6Bf2ftnwp4Q3smM35AKGlKNPZVvkvL3TVKhES5scq22O9950ClNt7XCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:20:20.490016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42cce52c541a24397d06f855a5242804fd84e2f602ce9995ab49a0f7548e5bc9","sha256:dd6929c9101c0fa61a251fd322bb28b65d33e899b5e79165b265ad6a1f55b8b8"],"state_sha256":"3262cc616c28c62dd366faa61cf1394469930fbaba34fb7836b8de2b96fceff4"}