{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VDKAFHVIQBGQGPNGNV2MPTDWOL","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":"f21f9348a172593d518c7962ad21bfb80e8da4bcc9c39b753439e75df417a213","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T23:22:59Z","title_canon_sha256":"df73e4635e8391feb6291ec8a9e7c0268d22b6f6b462fc2ac060130847f62727"},"schema_version":"1.0","source":{"id":"2212.08751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.08751","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"arxiv_version","alias_value":"2212.08751v1","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.08751","created_at":"2026-05-17T23:39:21Z"},{"alias_kind":"pith_short_12","alias_value":"VDKAFHVIQBGQ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"VDKAFHVIQBGQGPNG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"VDKAFHVI","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f8162325596284b77a7eb7c106e06a4ae85295633ec6d821a54a400163cb29ea","target":"graph","created_at":"2026-05-17T23:39:21Z","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":"Our method first generates a single synthetic view using a text-to-image diffusion model, and then produces a 3D point cloud using a second diffusion model which conditions on the generated image. ... produces 3D models in only 1-2 minutes on a single GPU."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single synthetic 2D view generated by the text-to-image model contains enough information for the second diffusion model to recover accurate 3D geometry for complex prompts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Point-E is a cascaded diffusion system that generates 3D point clouds from text in minutes by first synthesizing a 2D view then lifting it to 3D."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A two-stage diffusion process turns text prompts into 3D point clouds in 1-2 minutes on one GPU."}],"snapshot_sha256":"5e39034ff84f2df9fa7168a4bd601b781e54144619976805ae4c298c916d599e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3a6f18a3cc732cb7fe6b56166da9f2c8e20a96c8d506859fec384aa79bd604ba"},"paper":{"abstract_excerpt":"While recent work on text-conditional 3D object generation has shown promising results, the state-of-the-art methods typically require multiple GPU-hours to produce a single sample. This is in stark contrast to state-of-the-art generative image models, which produce samples in a number of seconds or minutes. In this paper, we explore an alternative method for 3D object generation which produces 3D models in only 1-2 minutes on a single GPU. Our method first generates a single synthetic view using a text-to-image diffusion model, and then produces a 3D point cloud using a second diffusion model","authors_text":"Alex Nichol, Heewoo Jun, Mark Chen, Pamela Mishkin, Prafulla Dhariwal","cross_cats":["cs.LG"],"headline":"A two-stage diffusion process turns text prompts into 3D point clouds in 1-2 minutes on one GPU.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T23:22:59Z","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.08751","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:46:07.223132Z","id":"b381caa9-b0e7-4fe5-b287-6b08e21df986","model_set":{"reader":"grok-4.3"},"one_line_summary":"Point-E is a cascaded diffusion system that generates 3D point clouds from text in minutes by first synthesizing a 2D view then lifting it to 3D.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A two-stage diffusion process turns text prompts into 3D point clouds in 1-2 minutes on one GPU.","strongest_claim":"Our method first generates a single synthetic view using a text-to-image diffusion model, and then produces a 3D point cloud using a second diffusion model which conditions on the generated image. ... produces 3D models in only 1-2 minutes on a single GPU.","weakest_assumption":"That a single synthetic 2D view generated by the text-to-image model contains enough information for the second diffusion model to recover accurate 3D geometry for complex prompts."}},"verdict_id":"b381caa9-b0e7-4fe5-b287-6b08e21df986"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3012021c327f7096b6ea654e90d5dea35796d21c3d16008e322128f911f9a840","target":"record","created_at":"2026-05-17T23:39:21Z","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":"f21f9348a172593d518c7962ad21bfb80e8da4bcc9c39b753439e75df417a213","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T23:22:59Z","title_canon_sha256":"df73e4635e8391feb6291ec8a9e7c0268d22b6f6b462fc2ac060130847f62727"},"schema_version":"1.0","source":{"id":"2212.08751","kind":"arxiv","version":1}},"canonical_sha256":"a8d4029ea8804d033da66d74c7cc7672d1dc83485250a44301225b098611f227","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8d4029ea8804d033da66d74c7cc7672d1dc83485250a44301225b098611f227","first_computed_at":"2026-05-17T23:39:21.773888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:21.773888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DIOBt4xTxMBPeUtAHHlw4FV9m8ep9deKSFGM198HBze0Exo8XtAJnkMAp5mrS7sC+jSZRQmheYkM6EJNayyMDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:21.774565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.08751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3012021c327f7096b6ea654e90d5dea35796d21c3d16008e322128f911f9a840","sha256:f8162325596284b77a7eb7c106e06a4ae85295633ec6d821a54a400163cb29ea"],"state_sha256":"09582306d8247cbb95a8960f536f4877e87521bbb580ce827fa83681982e0ae0"}