{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X4TY25NQHW46BYU56E7GVIXMS4","short_pith_number":"pith:X4TY25NQ","schema_version":"1.0","canonical_sha256":"bf278d75b03db9e0e29df13e6aa2ec973e27313d9faa82730e290abc69d0640a","source":{"kind":"arxiv","id":"2305.02463","version":1},"attestation_state":"computed","paper":{"title":"Shap-E: Generating Conditional 3D Implicit Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Nichol, Heewoo Jun","submitted_at":"2023-05-03T23:59:13Z","abstract_excerpt":"We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D generative models which produce a single output representation, Shap-E directly generates the parameters of implicit functions that can be rendered as both textured meshes and neural radiance fields. We train Shap-E in two stages: first, we train an encoder that deterministically maps 3D assets into the parameters of an implicit function; second, we train a conditional diffusion model on outputs of the encoder. When trained on a large dataset of paired 3D and text data, our resulting models are capable of"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2305.02463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T23:59:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"849263f58355d0a3194b14c6015d5d2a4ce1ca230f9388ad0c4f617cac30d80a","abstract_canon_sha256":"0d9d62f9c470ef444012dea373b4075f2ee687555e566b89393a360a207b5a22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.435370Z","signature_b64":"ybzy49v9fGsDBQ2FR+n/pU9Tjo+sHnIaEDnb25cVWqcB2yxhrPPvbA44h9HuHG8CK9mC18AXhf9cpeDoYGYlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf278d75b03db9e0e29df13e6aa2ec973e27313d9faa82730e290abc69d0640a","last_reissued_at":"2026-05-17T23:38:47.434855Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.434855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shap-E: Generating Conditional 3D Implicit Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alex Nichol, Heewoo Jun","submitted_at":"2023-05-03T23:59:13Z","abstract_excerpt":"We present Shap-E, a conditional generative model for 3D assets. Unlike recent work on 3D generative models which produce a single output representation, Shap-E directly generates the parameters of implicit functions that can be rendered as both textured meshes and neural radiance fields. We train Shap-E in two stages: first, we train an encoder that deterministically maps 3D assets into the parameters of an implicit function; second, we train a conditional diffusion model on outputs of the encoder. When trained on a large dataset of paired 3D and text data, our resulting models are capable of"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When trained on a large dataset of paired 3D and text data, our resulting models are capable of generating complex and diverse 3D assets in a matter of seconds.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The encoder stage can deterministically map arbitrary 3D assets into implicit-function parameters with negligible information loss, allowing the diffusion stage to operate in a faithful latent space.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"be0b99523b105351dba2745c1f12536c0934e252b31f1227cd477a22df1e1437"},"source":{"id":"2305.02463","kind":"arxiv","version":1},"verdict":{"id":"b8eca8b0-c0fd-4c1a-bd8d-9db32b723a91","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T15:27:46.007085Z","strongest_claim":"When trained on a large dataset of paired 3D and text data, our resulting models are capable of generating complex and diverse 3D assets in a matter of seconds.","one_line_summary":"Shap-E encodes 3D assets into implicit function parameters then uses a conditional diffusion model to generate new ones from text, enabling fast multi-representation 3D asset creation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The encoder stage can deterministically map arbitrary 3D assets into implicit-function parameters with negligible information loss, allowing the diffusion stage to operate in a faithful latent space.","pith_extraction_headline":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts."},"references":{"count":74,"sample":[{"doi":"","year":2017,"title":"Learning Representations and Generative Models for 3D Point Clouds","work_id":"cfca29dd-dc5d-468c-82c9-b34d1626c543","ref_index":1,"cited_arxiv_id":"1707.02392","is_internal_anchor":true},{"doi":"","year":2023,"title":"MusicLM: Generating Music From Text","work_id":"15e6566e-1c36-468f-966e-823248cbf87f","ref_index":2,"cited_arxiv_id":"2301.11325","is_internal_anchor":true},{"doi":"","year":2023,"title":"Sine: Semantic-driven image-based nerf editing with prior-guided editing field","work_id":"dc9dac60-a1c1-4d48-8c09-84a79db31c24","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Gaudi: A neural architect for immersive 3d scene generation","work_id":"c2453470-f4b6-48c9-96b8-0c6867b32eb0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Audiolm: a language modeling approach to audio generation","work_id":"3a2aea1c-8117-4436-9100-0536aea3cf47","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":74,"snapshot_sha256":"5d8ef6dbaf41d7fa61aeb0216a3adb0eae85fd1761e379fbea19bf2e532ebaa1","internal_anchors":33},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c55b0d76488cb727a41297b1494d15c8a3b79caf50ff097a3dbf931da3ac4b3e"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.02463","created_at":"2026-05-17T23:38:47.434937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02463v1","created_at":"2026-05-17T23:38:47.434937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02463","created_at":"2026-05-17T23:38:47.434937+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4TY25NQHW46","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4TY25NQHW46BYU5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4TY25NQ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":35,"internal_anchor_count":35,"sample":[{"citing_arxiv_id":"2401.16764","citing_title":"BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2504.02316","citing_title":"ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2508.04108","citing_title":"XARP Tools: An Extended Reality Platform for Humans and AI Agents","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16766","citing_title":"SVG360: Editable Multiview Vector Graphics from a Single SVG","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21472","citing_title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18430","citing_title":"Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18132","citing_title":"Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18052","citing_title":"Efficient 3D Content Reconstruction and Generation","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19876","citing_title":"Structural Energy Guidance for View-Consistent Text-to-3D Generation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16745","citing_title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16807","citing_title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04236","citing_title":"Scaling Sequence-to-Sequence Generative Neural Rendering","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2511.08416","citing_title":"Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05663","citing_title":"Objaverse-XL: A Universe of 10M+ 3D Objects","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2502.06608","citing_title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2412.01506","citing_title":"Structured 3D Latents for Scalable and Versatile 3D Generation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2601.09211","citing_title":"Affostruction: 3D Affordance Grounding with Generative Reconstruction","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2309.03453","citing_title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16653","citing_title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","ref_index":106,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04349","citing_title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2311.04400","citing_title":"LRM: Large Reconstruction Model for Single Image to 3D","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2308.16512","citing_title":"MVDream: Multi-view Diffusion for 3D Generation","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2404.07191","citing_title":"InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27504","citing_title":"REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4","json":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4.json","graph_json":"https://pith.science/api/pith-number/X4TY25NQHW46BYU56E7GVIXMS4/graph.json","events_json":"https://pith.science/api/pith-number/X4TY25NQHW46BYU56E7GVIXMS4/events.json","paper":"https://pith.science/paper/X4TY25NQ"},"agent_actions":{"view_html":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4","download_json":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4.json","view_paper":"https://pith.science/paper/X4TY25NQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02463&json=true","fetch_graph":"https://pith.science/api/pith-number/X4TY25NQHW46BYU56E7GVIXMS4/graph.json","fetch_events":"https://pith.science/api/pith-number/X4TY25NQHW46BYU56E7GVIXMS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4/action/storage_attestation","attest_author":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4/action/author_attestation","sign_citation":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4/action/citation_signature","submit_replication":"https://pith.science/pith/X4TY25NQHW46BYU56E7GVIXMS4/action/replication_record"}},"created_at":"2026-05-17T23:38:47.434937+00:00","updated_at":"2026-05-17T23:38:47.434937+00:00"}