{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FMXLIZQA2ART2NQOKAFIIS2ZCQ","short_pith_number":"pith:FMXLIZQA","canonical_record":{"source":{"id":"2308.16512","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T07:49:06Z","cross_cats_sorted":[],"title_canon_sha256":"27270046251efa8990a7ca4ed2d33c762601425c210d993eb51c6e174db65e07","abstract_canon_sha256":"86d2bbfa11e682f3b0b6d39426f8406902084f3e197a7e80234ff1f0c8640bde"},"schema_version":"1.0"},"canonical_sha256":"2b2eb46600d0233d360e500a844b5914142a957fcb9bd7bee406437a9fd86469","source":{"kind":"arxiv","id":"2308.16512","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16512","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16512v4","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16512","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"FMXLIZQA2ART","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FMXLIZQA2ART2NQO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FMXLIZQA","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FMXLIZQA2ART2NQOKAFIIS2ZCQ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.16512","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T07:49:06Z","cross_cats_sorted":[],"title_canon_sha256":"27270046251efa8990a7ca4ed2d33c762601425c210d993eb51c6e174db65e07","abstract_canon_sha256":"86d2bbfa11e682f3b0b6d39426f8406902084f3e197a7e80234ff1f0c8640bde"},"schema_version":"1.0"},"canonical_sha256":"2b2eb46600d0233d360e500a844b5914142a957fcb9bd7bee406437a9fd86469","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.011208Z","signature_b64":"icATlX3ryduVpX3fyvxz30MrCzJWvfjHksSUJ6zj9YIvzaiNi2LlXk3YLHTPeasyHc24dAZdPrSE645rZSIdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b2eb46600d0233d360e500a844b5914142a957fcb9bd7bee406437a9fd86469","last_reissued_at":"2026-05-17T23:38:53.010570Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.010570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.16512","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wNRG4+IscQmVzhuWpa6ZrXe/X8BO2aN0jBY89wEyPSHslgGRAsGVaLb4shdDvMGXdz+ylHhY+z9J0NxkGSeVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T22:30:33.248613Z"},"content_sha256":"e121d80da59cf698ab32ac4ff903c0c5414cb95cc385ccc2588417ca23933fc0","schema_version":"1.0","event_id":"sha256:e121d80da59cf698ab32ac4ff903c0c5414cb95cc385ccc2588417ca23933fc0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FMXLIZQA2ART2NQOKAFIIS2ZCQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MVDream: Multi-view Diffusion for 3D Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A multi-view diffusion model trained on both 2D and 3D data acts as a generalizable 3D prior that improves consistency in text-to-3D generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianglong Ye, Kejie Li, Mai Long, Peng Wang, Xiao Yang, Yichun Shi","submitted_at":"2023-08-31T07:49:06Z","abstract_excerpt":"We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt. Learning from both 2D and 3D data, a multi-view diffusion model can achieve the generalizability of 2D diffusion models and the consistency of 3D renderings. We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods. It can also learn new concepts from a few 2"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That joint training on 2D and 3D data produces a prior that remains generalizable to novel text prompts and 3D shapes without overfitting to the specific 3D renderings used or sacrificing single-view quality.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MVDream is a multi-view diffusion model that functions as a generalizable 3D prior, enabling more consistent text-to-3D generation and few-shot 3D concept learning from 2D examples.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A multi-view diffusion model trained on both 2D and 3D data acts as a generalizable 3D prior that improves consistency in text-to-3D generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4d472f64f3c14e59151f739b6333b0fef61973fa7492b6460feae3086ce71405"},"source":{"id":"2308.16512","kind":"arxiv","version":4},"verdict":{"id":"0a18a511-cce3-431b-b005-758833fd1b28","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T08:31:50.509985Z","strongest_claim":"We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods.","one_line_summary":"MVDream is a multi-view diffusion model that functions as a generalizable 3D prior, enabling more consistent text-to-3D generation and few-shot 3D concept learning from 2D examples.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That joint training on 2D and 3D data produces a prior that remains generalizable to novel text prompts and 3D shapes without overfitting to the specific 3D renderings used or sacrificing single-view quality.","pith_extraction_headline":"A multi-view diffusion model trained on both 2D and 3D data acts as a generalizable 3D prior that improves consistency in text-to-3D generation."},"references":{"count":161,"sample":[{"doi":"","year":2023,"title":"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0","work_id":"bca32d14-ca0e-45d5-aabb-29735f777c42","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"https://sketchfab.com/3d-models/popular","work_id":"b2699ee7-f789-4b50-968f-62e0fbf6f7a7","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"https://huggingface.co/DeepFloyd","work_id":"0804d3f6-1aaa-4ec4-a0fc-cbc41b1f14d6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"https://lumalabs.ai/dashboard/imagine","work_id":"8ceb3039-f241-407f-b9d8-ce4b2e13ee17","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"https://huggingface.co/spaces/lambdalabs/stable-diffusion-image-variations","work_id":"5faab264-b3c9-45c5-80eb-71dc59ff0c18","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":161,"snapshot_sha256":"e6b46909af3c518bf1f71bab7612cb73cd6eb27d5d6f6c85a75393bc270793e4","internal_anchors":10},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9909097488ee0cf5b31d5b3c6738472d570a3600b5c45167e05e0998051ec760"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0a18a511-cce3-431b-b005-758833fd1b28"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EdrsuzhcBnGB8XuBOepl3Xv/DsmgPT5kKrHZ7AZU82hkrpnik5g8AbU/tl1fAPY3aAIQWF5in18z1wF4tIxGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T22:30:33.249608Z"},"content_sha256":"62d7e54e6aa483cd8114fc6bd62ebef89e2b8627278dbef4f4e3df7c22f698d4","schema_version":"1.0","event_id":"sha256:62d7e54e6aa483cd8114fc6bd62ebef89e2b8627278dbef4f4e3df7c22f698d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ/bundle.json","state_url":"https://pith.science/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ/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":"2026-06-06T22:30:33Z","links":{"resolver":"https://pith.science/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ","bundle":"https://pith.science/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ/bundle.json","state":"https://pith.science/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMXLIZQA2ART2NQOKAFIIS2ZCQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FMXLIZQA2ART2NQOKAFIIS2ZCQ","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":"86d2bbfa11e682f3b0b6d39426f8406902084f3e197a7e80234ff1f0c8640bde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T07:49:06Z","title_canon_sha256":"27270046251efa8990a7ca4ed2d33c762601425c210d993eb51c6e174db65e07"},"schema_version":"1.0","source":{"id":"2308.16512","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16512","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16512v4","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16512","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"FMXLIZQA2ART","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"FMXLIZQA2ART2NQO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"FMXLIZQA","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:62d7e54e6aa483cd8114fc6bd62ebef89e2b8627278dbef4f4e3df7c22f698d4","target":"graph","created_at":"2026-05-17T23:38:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That joint training on 2D and 3D data produces a prior that remains generalizable to novel text prompts and 3D shapes without overfitting to the specific 3D renderings used or sacrificing single-view quality."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MVDream is a multi-view diffusion model that functions as a generalizable 3D prior, enabling more consistent text-to-3D generation and few-shot 3D concept learning from 2D examples."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A multi-view diffusion model trained on both 2D and 3D data acts as a generalizable 3D prior that improves consistency in text-to-3D generation."}],"snapshot_sha256":"4d472f64f3c14e59151f739b6333b0fef61973fa7492b6460feae3086ce71405"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9909097488ee0cf5b31d5b3c6738472d570a3600b5c45167e05e0998051ec760"},"paper":{"abstract_excerpt":"We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt. Learning from both 2D and 3D data, a multi-view diffusion model can achieve the generalizability of 2D diffusion models and the consistency of 3D renderings. We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods. It can also learn new concepts from a few 2","authors_text":"Jianglong Ye, Kejie Li, Mai Long, Peng Wang, Xiao Yang, Yichun Shi","cross_cats":[],"headline":"A multi-view diffusion model trained on both 2D and 3D data acts as a generalizable 3D prior that improves consistency in text-to-3D generation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T07:49:06Z","title":"MVDream: Multi-view Diffusion for 3D Generation"},"references":{"count":161,"internal_anchors":10,"resolved_work":161,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0","work_id":"bca32d14-ca0e-45d5-aabb-29735f777c42","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"https://sketchfab.com/3d-models/popular","work_id":"b2699ee7-f789-4b50-968f-62e0fbf6f7a7","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"https://huggingface.co/DeepFloyd","work_id":"0804d3f6-1aaa-4ec4-a0fc-cbc41b1f14d6","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"https://lumalabs.ai/dashboard/imagine","work_id":"8ceb3039-f241-407f-b9d8-ce4b2e13ee17","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"https://huggingface.co/spaces/lambdalabs/stable-diffusion-image-variations","work_id":"5faab264-b3c9-45c5-80eb-71dc59ff0c18","year":null}],"snapshot_sha256":"e6b46909af3c518bf1f71bab7612cb73cd6eb27d5d6f6c85a75393bc270793e4"},"source":{"id":"2308.16512","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T08:31:50.509985Z","id":"0a18a511-cce3-431b-b005-758833fd1b28","model_set":{"reader":"grok-4.3"},"one_line_summary":"MVDream is a multi-view diffusion model that functions as a generalizable 3D prior, enabling more consistent text-to-3D generation and few-shot 3D concept learning from 2D examples.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A multi-view diffusion model trained on both 2D and 3D data acts as a generalizable 3D prior that improves consistency in text-to-3D generation.","strongest_claim":"We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods.","weakest_assumption":"That joint training on 2D and 3D data produces a prior that remains generalizable to novel text prompts and 3D shapes without overfitting to the specific 3D renderings used or sacrificing single-view quality."}},"verdict_id":"0a18a511-cce3-431b-b005-758833fd1b28"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e121d80da59cf698ab32ac4ff903c0c5414cb95cc385ccc2588417ca23933fc0","target":"record","created_at":"2026-05-17T23:38:53Z","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":"86d2bbfa11e682f3b0b6d39426f8406902084f3e197a7e80234ff1f0c8640bde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-31T07:49:06Z","title_canon_sha256":"27270046251efa8990a7ca4ed2d33c762601425c210d993eb51c6e174db65e07"},"schema_version":"1.0","source":{"id":"2308.16512","kind":"arxiv","version":4}},"canonical_sha256":"2b2eb46600d0233d360e500a844b5914142a957fcb9bd7bee406437a9fd86469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b2eb46600d0233d360e500a844b5914142a957fcb9bd7bee406437a9fd86469","first_computed_at":"2026-05-17T23:38:53.010570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.010570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icATlX3ryduVpX3fyvxz30MrCzJWvfjHksSUJ6zj9YIvzaiNi2LlXk3YLHTPeasyHc24dAZdPrSE645rZSIdCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.011208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16512","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e121d80da59cf698ab32ac4ff903c0c5414cb95cc385ccc2588417ca23933fc0","sha256:62d7e54e6aa483cd8114fc6bd62ebef89e2b8627278dbef4f4e3df7c22f698d4"],"state_sha256":"1de45ae85fa80b88fc88ba8d138ca49af87c4ab535a96041ac0b52f5f933905e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Unn5uKoGf0p6UowdWShB+CWuBRESDnGwGY3t0sEzb4mLQY7ius2YOMCMls01vUeSl7P4rYHqagQEhiGkC/6bDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T22:30:33.254186Z","bundle_sha256":"854c16de609d1a632874b7e0f1a81c3662913089c06231f1c071f534400ab3b2"}}