{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JTDCJ3GRYSNF4PRMGO6WYJX5BE","short_pith_number":"pith:JTDCJ3GR","canonical_record":{"source":{"id":"2404.18065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-28T04:05:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"258970502d275e02d14fe31c4c6f99bc492f8f3c3d66d714fc077c30f6b0e9bb","abstract_canon_sha256":"c2426c1d1cdc30ad6f59381eb02e641eb1ae80a0389ba767fe1847616e4a3b01"},"schema_version":"1.0"},"canonical_sha256":"4cc624ecd1c49a5e3e2c33bd6c26fd093487f07cf991217bca5943e90a3b5471","source":{"kind":"arxiv","id":"2404.18065","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18065","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18065v1","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18065","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"JTDCJ3GRYSNF","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"JTDCJ3GRYSNF4PRM","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"JTDCJ3GR","created_at":"2026-07-05T08:12:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JTDCJ3GRYSNF4PRMGO6WYJX5BE","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18065","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-28T04:05:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"258970502d275e02d14fe31c4c6f99bc492f8f3c3d66d714fc077c30f6b0e9bb","abstract_canon_sha256":"c2426c1d1cdc30ad6f59381eb02e641eb1ae80a0389ba767fe1847616e4a3b01"},"schema_version":"1.0"},"canonical_sha256":"4cc624ecd1c49a5e3e2c33bd6c26fd093487f07cf991217bca5943e90a3b5471","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:57.902810Z","signature_b64":"K8CI2k2fKfHd8LqB78sg41oFfeMlqXzc2OQJKLWfBGcXq3Hgj5gjf+34v3/AYpElDBM4vgwmgaK46Dp4foSlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cc624ecd1c49a5e3e2c33bd6c26fd093487f07cf991217bca5943e90a3b5471","last_reissued_at":"2026-07-05T08:12:57.902336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:57.902336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18065","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lg2r1Ba2imCdevHadkrYXQDn1xLPOhz9Ya/jbNlmjxLSCZhs/Etzw8YoOBBXhx88ZmhDYYuuy3CkruiKMNbVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:06:24.311761Z"},"content_sha256":"17350517dc8bd2f70e188e54e22cd928ab016a20bf7aa807722e9305dd4e1558","schema_version":"1.0","event_id":"sha256:17350517dc8bd2f70e188e54e22cd928ab016a20bf7aa807722e9305dd4e1558"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JTDCJ3GRYSNF4PRMGO6WYJX5BE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ashwin Swaminathan, Chethan Parameshwara, Cj Taylor, Jiawei Mo, Paolo Favaro, Stefano Soatto, Xiaohan Fei, Xiaolong Li, Ying Wang, Zhuowen Tu","submitted_at":"2024-04-28T04:05:10Z","abstract_excerpt":"In this paper, we propose an effective two-stage approach named Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts while achieving high fidelity by using a pre-trained multi-view diffusion model. Multi-view diffusion models, such as MVDream, have shown to generate high-fidelity 3D assets using score distillation sampling (SDS). However, applied naively, these methods often fail to comprehend compositional text prompts, and may often entirely omit certain subjects or parts. To address this issue, we first advocate leveraging text-guided 4-view "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18065","kind":"arxiv","version":1},"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/2404.18065/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6jAEBbUhpCVKFpgE4S+YKfM99h01Rc2mZJlr2qKvkU3z2pVCyIBXaKY9K22lQIJmWWrfENYZdCZUpCQBzX5mAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:06:24.312136Z"},"content_sha256":"2695b62d380fe6476f7e602a0755372564264c5b8194d698ad81390c0019b446","schema_version":"1.0","event_id":"sha256:2695b62d380fe6476f7e602a0755372564264c5b8194d698ad81390c0019b446"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE/bundle.json","state_url":"https://pith.science/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T08:06:24Z","links":{"resolver":"https://pith.science/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE","bundle":"https://pith.science/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE/bundle.json","state":"https://pith.science/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JTDCJ3GRYSNF4PRMGO6WYJX5BE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JTDCJ3GRYSNF4PRMGO6WYJX5BE","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":"c2426c1d1cdc30ad6f59381eb02e641eb1ae80a0389ba767fe1847616e4a3b01","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-28T04:05:10Z","title_canon_sha256":"258970502d275e02d14fe31c4c6f99bc492f8f3c3d66d714fc077c30f6b0e9bb"},"schema_version":"1.0","source":{"id":"2404.18065","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18065","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18065v1","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18065","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"pith_short_12","alias_value":"JTDCJ3GRYSNF","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"pith_short_16","alias_value":"JTDCJ3GRYSNF4PRM","created_at":"2026-07-05T08:12:57Z"},{"alias_kind":"pith_short_8","alias_value":"JTDCJ3GR","created_at":"2026-07-05T08:12:57Z"}],"graph_snapshots":[{"event_id":"sha256:2695b62d380fe6476f7e602a0755372564264c5b8194d698ad81390c0019b446","target":"graph","created_at":"2026-07-05T08:12:57Z","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/2404.18065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose an effective two-stage approach named Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts while achieving high fidelity by using a pre-trained multi-view diffusion model. Multi-view diffusion models, such as MVDream, have shown to generate high-fidelity 3D assets using score distillation sampling (SDS). However, applied naively, these methods often fail to comprehend compositional text prompts, and may often entirely omit certain subjects or parts. To address this issue, we first advocate leveraging text-guided 4-view ","authors_text":"Ashwin Swaminathan, Chethan Parameshwara, Cj Taylor, Jiawei Mo, Paolo Favaro, Stefano Soatto, Xiaohan Fei, Xiaolong Li, Ying Wang, Zhuowen Tu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-28T04:05:10Z","title":"Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18065","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":"sha256:17350517dc8bd2f70e188e54e22cd928ab016a20bf7aa807722e9305dd4e1558","target":"record","created_at":"2026-07-05T08:12:57Z","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":"c2426c1d1cdc30ad6f59381eb02e641eb1ae80a0389ba767fe1847616e4a3b01","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-28T04:05:10Z","title_canon_sha256":"258970502d275e02d14fe31c4c6f99bc492f8f3c3d66d714fc077c30f6b0e9bb"},"schema_version":"1.0","source":{"id":"2404.18065","kind":"arxiv","version":1}},"canonical_sha256":"4cc624ecd1c49a5e3e2c33bd6c26fd093487f07cf991217bca5943e90a3b5471","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cc624ecd1c49a5e3e2c33bd6c26fd093487f07cf991217bca5943e90a3b5471","first_computed_at":"2026-07-05T08:12:57.902336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:57.902336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K8CI2k2fKfHd8LqB78sg41oFfeMlqXzc2OQJKLWfBGcXq3Hgj5gjf+34v3/AYpElDBM4vgwmgaK46Dp4foSlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:57.902810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18065","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17350517dc8bd2f70e188e54e22cd928ab016a20bf7aa807722e9305dd4e1558","sha256:2695b62d380fe6476f7e602a0755372564264c5b8194d698ad81390c0019b446"],"state_sha256":"9d1ea6a686bb8fad9530e6ed8a676b3dca815ad4dfb59c79b8a3fddd61ee8774"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIj8Qm/vteQ/EOF9Mej89FqFDEJT4AzLIiIoJexx0HJJgukDq+Rk8MIIGZy4w46PwVcrJac/jsHtQRum9kwOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:06:24.314145Z","bundle_sha256":"cd255ae27442e8f7ab4fa9db621aca7142552d4eda3277d112cbe297ff2b6aab"}}