{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:X4TY25NQHW46BYU56E7GVIXMS4","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":"0d9d62f9c470ef444012dea373b4075f2ee687555e566b89393a360a207b5a22","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T23:59:13Z","title_canon_sha256":"849263f58355d0a3194b14c6015d5d2a4ce1ca230f9388ad0c4f617cac30d80a"},"schema_version":"1.0","source":{"id":"2305.02463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02463","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02463v1","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02463","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"X4TY25NQHW46","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"X4TY25NQHW46BYU5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"X4TY25NQ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fe406cb046563195677269e15825ef10a8c487b43602dfc8921bc9b08f9199b8","target":"graph","created_at":"2026-05-17T23:38:47Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts."}],"snapshot_sha256":"be0b99523b105351dba2745c1f12536c0934e252b31f1227cd477a22df1e1437"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c55b0d76488cb727a41297b1494d15c8a3b79caf50ff097a3dbf931da3ac4b3e"},"paper":{"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","authors_text":"Alex Nichol, Heewoo Jun","cross_cats":["cs.LG"],"headline":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T23:59:13Z","title":"Shap-E: Generating Conditional 3D Implicit Functions"},"references":{"count":74,"internal_anchors":33,"resolved_work":74,"sample":[{"cited_arxiv_id":"1707.02392","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Learning Representations and Generative Models for 3D Point Clouds","work_id":"cfca29dd-dc5d-468c-82c9-b34d1626c543","year":2017},{"cited_arxiv_id":"2301.11325","doi":"","is_internal_anchor":true,"ref_index":2,"title":"MusicLM: Generating Music From Text","work_id":"15e6566e-1c36-468f-966e-823248cbf87f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Sine: Semantic-driven image-based nerf editing with prior-guided editing field","work_id":"dc9dac60-a1c1-4d48-8c09-84a79db31c24","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Gaudi: A neural architect for immersive 3d scene generation","work_id":"c2453470-f4b6-48c9-96b8-0c6867b32eb0","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Audiolm: a language modeling approach to audio generation","work_id":"3a2aea1c-8117-4436-9100-0536aea3cf47","year":2022}],"snapshot_sha256":"5d8ef6dbaf41d7fa61aeb0216a3adb0eae85fd1761e379fbea19bf2e532ebaa1"},"source":{"id":"2305.02463","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-16T15:27:46.007085Z","id":"b8eca8b0-c0fd-4c1a-bd8d-9db32b723a91","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Shap-E generates parameters of implicit functions for 3D assets directly from text prompts.","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.","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."}},"verdict_id":"b8eca8b0-c0fd-4c1a-bd8d-9db32b723a91"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:135b1c6e8a7f05354275cdad7dca3a3e5a40b164397d91b5354c0a74c219a77d","target":"record","created_at":"2026-05-17T23:38:47Z","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":"0d9d62f9c470ef444012dea373b4075f2ee687555e566b89393a360a207b5a22","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-03T23:59:13Z","title_canon_sha256":"849263f58355d0a3194b14c6015d5d2a4ce1ca230f9388ad0c4f617cac30d80a"},"schema_version":"1.0","source":{"id":"2305.02463","kind":"arxiv","version":1}},"canonical_sha256":"bf278d75b03db9e0e29df13e6aa2ec973e27313d9faa82730e290abc69d0640a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf278d75b03db9e0e29df13e6aa2ec973e27313d9faa82730e290abc69d0640a","first_computed_at":"2026-05-17T23:38:47.434855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.434855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ybzy49v9fGsDBQ2FR+n/pU9Tjo+sHnIaEDnb25cVWqcB2yxhrPPvbA44h9HuHG8CK9mC18AXhf9cpeDoYGYlBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.435370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:135b1c6e8a7f05354275cdad7dca3a3e5a40b164397d91b5354c0a74c219a77d","sha256:fe406cb046563195677269e15825ef10a8c487b43602dfc8921bc9b08f9199b8"],"state_sha256":"47d127239daca15f2a9d76537f74bef7af7ea9a8831332b3a399dbfd322a1856"}