{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FXBKTFKEVPEJIAQVSW5C7DBXXZ","short_pith_number":"pith:FXBKTFKE","schema_version":"1.0","canonical_sha256":"2dc2a99544abc894021595ba2f8c37be5fd6a2756bf1268e5e06e65a903cdf1d","source":{"kind":"arxiv","id":"2402.16994","version":2},"attestation_state":"computed","paper":{"title":"GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dmitry Petrov, Evangelos Kalogerakis, Matheus Gadelha, Melinos Averkiou, Pradyumn Goyal, Siddhartha Chaudhuri, Vikas Thamizharasan, Vladimir G. Kim","submitted_at":"2024-02-26T20:00:57Z","abstract_excerpt":"We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes. The key ingredient of our method is a neural skeleton-based representation encoding information on both shape topology and geometry. Through a denoising diffusion probabilistic model, our method first generates skeleton-based representations following the Medial Axis Transform (MAT), then generates surfaces through a skeleton-driven neural implicit formulation. The neural implicit takes into account the topological and geometric information stored in the generated skeleton representations to yield surfaces that are"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.16994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-26T20:00:57Z","cross_cats_sorted":["cs.AI","cs.GR","cs.LG"],"title_canon_sha256":"d276c57b8202791725d7a2d44950e84d55719c82ecc2388a94bdc87934c98329","abstract_canon_sha256":"ec849fe3c992884a4e7d6e348e688c8d4a58cad63e88988e089a5665475d4a4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:46.947129Z","signature_b64":"DMwsSdHkpaL31KF2imgZ8gBY8HnXf0qMuFh5fmrRD+2F84mxePPUxxs/8s1lPEvNi2+K5u7s2Vsd0w7kozgVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dc2a99544abc894021595ba2f8c37be5fd6a2756bf1268e5e06e65a903cdf1d","last_reissued_at":"2026-07-05T08:06:46.946639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:46.946639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GEM3D: GEnerative Medial Abstractions for 3D Shape Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dmitry Petrov, Evangelos Kalogerakis, Matheus Gadelha, Melinos Averkiou, Pradyumn Goyal, Siddhartha Chaudhuri, Vikas Thamizharasan, Vladimir G. Kim","submitted_at":"2024-02-26T20:00:57Z","abstract_excerpt":"We introduce GEM3D -- a new deep, topology-aware generative model of 3D shapes. The key ingredient of our method is a neural skeleton-based representation encoding information on both shape topology and geometry. Through a denoising diffusion probabilistic model, our method first generates skeleton-based representations following the Medial Axis Transform (MAT), then generates surfaces through a skeleton-driven neural implicit formulation. The neural implicit takes into account the topological and geometric information stored in the generated skeleton representations to yield surfaces that are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16994","kind":"arxiv","version":2},"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/2402.16994/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.16994","created_at":"2026-07-05T08:06:46.946698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16994v2","created_at":"2026-07-05T08:06:46.946698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16994","created_at":"2026-07-05T08:06:46.946698+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXBKTFKEVPEJ","created_at":"2026-07-05T08:06:46.946698+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXBKTFKEVPEJIAQV","created_at":"2026-07-05T08:06:46.946698+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXBKTFKE","created_at":"2026-07-05T08:06:46.946698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06600","citing_title":"RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ","json":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ.json","graph_json":"https://pith.science/api/pith-number/FXBKTFKEVPEJIAQVSW5C7DBXXZ/graph.json","events_json":"https://pith.science/api/pith-number/FXBKTFKEVPEJIAQVSW5C7DBXXZ/events.json","paper":"https://pith.science/paper/FXBKTFKE"},"agent_actions":{"view_html":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ","download_json":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ.json","view_paper":"https://pith.science/paper/FXBKTFKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16994&json=true","fetch_graph":"https://pith.science/api/pith-number/FXBKTFKEVPEJIAQVSW5C7DBXXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FXBKTFKEVPEJIAQVSW5C7DBXXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ/action/storage_attestation","attest_author":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ/action/author_attestation","sign_citation":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ/action/citation_signature","submit_replication":"https://pith.science/pith/FXBKTFKEVPEJIAQVSW5C7DBXXZ/action/replication_record"}},"created_at":"2026-07-05T08:06:46.946698+00:00","updated_at":"2026-07-05T08:06:46.946698+00:00"}