{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:74I5OMS2A4BQ3VBFWQK54ENBTR","short_pith_number":"pith:74I5OMS2","schema_version":"1.0","canonical_sha256":"ff11d7325a07030dd425b415de11a19c7e0050dddd0354a1b10910a904c580d3","source":{"kind":"arxiv","id":"2409.18114","version":1},"attestation_state":"computed","paper":{"title":"EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Zeng, Jiaxiang Tang, Ming-Yu Liu, Qinsheng Zhang, Xian Liu, Zekun Hao, Zhaoshuo Li","submitted_at":"2024-09-26T17:55:02Z","abstract_excerpt":"Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of $512^3$. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training lat"},"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":"2409.18114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-26T17:55:02Z","cross_cats_sorted":[],"title_canon_sha256":"46aed75aced9339400aecd22546fc3df108c54fdf2379cf3afb229cbdb6d42b4","abstract_canon_sha256":"82a1ce1c611d9eb1bb1458278b015d73d3c389f693cc585f1b76d1ae4ec3125c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:20.902783Z","signature_b64":"qfhCh9yIh6f9kbR9vJ/M7MsaTUOnYEDR5srZREI64O1la2jaC2zZ2qqGlXO30yEblO3gzC3w4eajvAU6S36FDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff11d7325a07030dd425b415de11a19c7e0050dddd0354a1b10910a904c580d3","last_reissued_at":"2026-07-05T09:12:20.902240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:20.902240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gang Zeng, Jiaxiang Tang, Ming-Yu Liu, Qinsheng Zhang, Xian Liu, Zekun Hao, Zhaoshuo Li","submitted_at":"2024-09-26T17:55:02Z","abstract_excerpt":"Current auto-regressive mesh generation methods suffer from issues such as incompleteness, insufficient detail, and poor generalization. In this paper, we propose an Auto-regressive Auto-encoder (ArAE) model capable of generating high-quality 3D meshes with up to 4,000 faces at a spatial resolution of $512^3$. We introduce a novel mesh tokenization algorithm that efficiently compresses triangular meshes into 1D token sequences, significantly enhancing training efficiency. Furthermore, our model compresses variable-length triangular meshes into a fixed-length latent space, enabling training lat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18114","kind":"arxiv","version":1},"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/2409.18114/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":"2409.18114","created_at":"2026-07-05T09:12:20.902305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18114v1","created_at":"2026-07-05T09:12:20.902305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18114","created_at":"2026-07-05T09:12:20.902305+00:00"},{"alias_kind":"pith_short_12","alias_value":"74I5OMS2A4BQ","created_at":"2026-07-05T09:12:20.902305+00:00"},{"alias_kind":"pith_short_16","alias_value":"74I5OMS2A4BQ3VBF","created_at":"2026-07-05T09:12:20.902305+00:00"},{"alias_kind":"pith_short_8","alias_value":"74I5OMS2","created_at":"2026-07-05T09:12:20.902305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24138","citing_title":"Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23489","citing_title":"MeshFlow: Mesh Generation with Equivariant Flow Matching","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20131","citing_title":"TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04621","citing_title":"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26182","citing_title":"BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29655","citing_title":"SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2501.12202","citing_title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17620","citing_title":"SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16813","citing_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22858","citing_title":"Learning to Build Shapes by Extrusion","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14594","citing_title":"TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01479","citing_title":"UniRecGen: Unifying Multi-View 3D Reconstruction and Generation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23629","citing_title":"From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20539","citing_title":"Animator-Centric Skeleton Generation on Objects with Fine-Grained Details","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR","json":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR.json","graph_json":"https://pith.science/api/pith-number/74I5OMS2A4BQ3VBFWQK54ENBTR/graph.json","events_json":"https://pith.science/api/pith-number/74I5OMS2A4BQ3VBFWQK54ENBTR/events.json","paper":"https://pith.science/paper/74I5OMS2"},"agent_actions":{"view_html":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR","download_json":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR.json","view_paper":"https://pith.science/paper/74I5OMS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18114&json=true","fetch_graph":"https://pith.science/api/pith-number/74I5OMS2A4BQ3VBFWQK54ENBTR/graph.json","fetch_events":"https://pith.science/api/pith-number/74I5OMS2A4BQ3VBFWQK54ENBTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR/action/storage_attestation","attest_author":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR/action/author_attestation","sign_citation":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR/action/citation_signature","submit_replication":"https://pith.science/pith/74I5OMS2A4BQ3VBFWQK54ENBTR/action/replication_record"}},"created_at":"2026-07-05T09:12:20.902305+00:00","updated_at":"2026-07-05T09:12:20.902305+00:00"}