{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QAPFYDGCTY7OMARQXCMAHTDYOQ","short_pith_number":"pith:QAPFYDGC","schema_version":"1.0","canonical_sha256":"801e5c0cc29e3ee60230b89803cc787409ef30a7bbcf4ab6075142d081466ae6","source":{"kind":"arxiv","id":"2503.16653","version":2},"attestation_state":"computed","paper":{"title":"iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Zhang, Dong-Ming Yan, Hanxiao Wang, Peter Wonka, Weize Quan","submitted_at":"2025-03-20T19:10:37Z","abstract_excerpt":"This paper propose iFlame, a novel transformer-based network architecture for mesh generation. While attention-based models have demonstrated remarkable performance in mesh generation, their quadratic computational complexity limits scalability, particularly for high-resolution 3D data. Conversely, linear attention mechanisms offer lower computational costs but often struggle to capture long-range dependencies, resulting in suboptimal outcomes. To address this trade-off, we propose an interleaving autoregressive mesh generation framework that combines the efficiency of linear attention with th"},"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":"2503.16653","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T19:10:37Z","cross_cats_sorted":[],"title_canon_sha256":"51ac107001e5057db959d76ab71c010c2ab887a0ec918b07bf25841f8c92399b","abstract_canon_sha256":"54204887961760e96c8a9dc048995aed152a03073f9992c73ba5a41b5093fe3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:48.837494Z","signature_b64":"13amXf0JkfaqMzFO07f5Sdxh+a5CYbnZcDz657XgkqbpGhthQ/3/6SUyg7sakGHcH2F1243QrIgvoxK+RkOiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"801e5c0cc29e3ee60230b89803cc787409ef30a7bbcf4ab6075142d081466ae6","last_reissued_at":"2026-07-05T10:37:48.836903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:48.836903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Biao Zhang, Dong-Ming Yan, Hanxiao Wang, Peter Wonka, Weize Quan","submitted_at":"2025-03-20T19:10:37Z","abstract_excerpt":"This paper propose iFlame, a novel transformer-based network architecture for mesh generation. While attention-based models have demonstrated remarkable performance in mesh generation, their quadratic computational complexity limits scalability, particularly for high-resolution 3D data. Conversely, linear attention mechanisms offer lower computational costs but often struggle to capture long-range dependencies, resulting in suboptimal outcomes. To address this trade-off, we propose an interleaving autoregressive mesh generation framework that combines the efficiency of linear attention with th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16653","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/2503.16653/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":"2503.16653","created_at":"2026-07-05T10:37:48.836981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16653v2","created_at":"2026-07-05T10:37:48.836981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16653","created_at":"2026-07-05T10:37:48.836981+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAPFYDGCTY7O","created_at":"2026-07-05T10:37:48.836981+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAPFYDGCTY7OMARQ","created_at":"2026-07-05T10:37:48.836981+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAPFYDGC","created_at":"2026-07-05T10:37:48.836981+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23489","citing_title":"MeshFlow: Mesh Generation with Equivariant Flow Matching","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04688","citing_title":"MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16813","citing_title":"QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14594","citing_title":"TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation","ref_index":71,"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":180,"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":180,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ","json":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ.json","graph_json":"https://pith.science/api/pith-number/QAPFYDGCTY7OMARQXCMAHTDYOQ/graph.json","events_json":"https://pith.science/api/pith-number/QAPFYDGCTY7OMARQXCMAHTDYOQ/events.json","paper":"https://pith.science/paper/QAPFYDGC"},"agent_actions":{"view_html":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ","download_json":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ.json","view_paper":"https://pith.science/paper/QAPFYDGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16653&json=true","fetch_graph":"https://pith.science/api/pith-number/QAPFYDGCTY7OMARQXCMAHTDYOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QAPFYDGCTY7OMARQXCMAHTDYOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ/action/storage_attestation","attest_author":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ/action/author_attestation","sign_citation":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ/action/citation_signature","submit_replication":"https://pith.science/pith/QAPFYDGCTY7OMARQXCMAHTDYOQ/action/replication_record"}},"created_at":"2026-07-05T10:37:48.836981+00:00","updated_at":"2026-07-05T10:37:48.836981+00:00"}