{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UXNGYAMW62CNOQ2GRF2W3XTWDC","short_pith_number":"pith:UXNGYAMW","schema_version":"1.0","canonical_sha256":"a5da6c0196f684d7434689756dde7618b51e0e313f257881ee8fc6796596ff2b","source":{"kind":"arxiv","id":"2505.13573","version":1},"attestation_state":"computed","paper":{"title":"FreeMesh: Boosting Mesh Generation with Coordinates Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GR","authors_text":"Biwen Lei, Chunchao Guo, Haohan Weng, Jian Liu, Song Guo, Tao Han, Xianghui Yang, Zhuo Chen, Zibo Zhao","submitted_at":"2025-05-19T13:52:57Z","abstract_excerpt":"The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshes into sequences. In this paper, we introduce a new metric Per-Token-Mesh-Entropy (PTME) to evaluate the existing mesh tokenizers theoretically without any training. Building upon PTME, we propose a plug-and-play tokenization technique called coordinate merging. It further improves the compression ratios of existing tokenizers by rearranging and merging the m"},"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":"2505.13573","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2025-05-19T13:52:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c94bf21b1128728596c07dbe0a7e77aeb5888ee6e157eecdc79f1b3a07d72305","abstract_canon_sha256":"8a84ddf3e8ec48c8ed94c4d0d1a7204eb4572dfac1474d38d2e59115852306cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:47.976089Z","signature_b64":"rPMY6W0NIZF543PPp2YtG6gkufAiR97jM4sRkqvpVnb5CEVAdHSL+TJRvDZ4p652KhO7WVVl1aU4b1AOiuYyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5da6c0196f684d7434689756dde7618b51e0e313f257881ee8fc6796596ff2b","last_reissued_at":"2026-07-05T11:05:47.975556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:47.975556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeMesh: Boosting Mesh Generation with Coordinates Merging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GR","authors_text":"Biwen Lei, Chunchao Guo, Haohan Weng, Jian Liu, Song Guo, Tao Han, Xianghui Yang, Zhuo Chen, Zibo Zhao","submitted_at":"2025-05-19T13:52:57Z","abstract_excerpt":"The next-coordinate prediction paradigm has emerged as the de facto standard in current auto-regressive mesh generation methods. Despite their effectiveness, there is no efficient measurement for the various tokenizers that serialize meshes into sequences. In this paper, we introduce a new metric Per-Token-Mesh-Entropy (PTME) to evaluate the existing mesh tokenizers theoretically without any training. Building upon PTME, we propose a plug-and-play tokenization technique called coordinate merging. It further improves the compression ratios of existing tokenizers by rearranging and merging the m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13573","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/2505.13573/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":"2505.13573","created_at":"2026-07-05T11:05:47.975610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13573v1","created_at":"2026-07-05T11:05:47.975610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13573","created_at":"2026-07-05T11:05:47.975610+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXNGYAMW62CN","created_at":"2026-07-05T11:05:47.975610+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXNGYAMW62CNOQ2G","created_at":"2026-07-05T11:05:47.975610+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXNGYAMW","created_at":"2026-07-05T11:05:47.975610+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14594","citing_title":"TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC","json":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC.json","graph_json":"https://pith.science/api/pith-number/UXNGYAMW62CNOQ2GRF2W3XTWDC/graph.json","events_json":"https://pith.science/api/pith-number/UXNGYAMW62CNOQ2GRF2W3XTWDC/events.json","paper":"https://pith.science/paper/UXNGYAMW"},"agent_actions":{"view_html":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC","download_json":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC.json","view_paper":"https://pith.science/paper/UXNGYAMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13573&json=true","fetch_graph":"https://pith.science/api/pith-number/UXNGYAMW62CNOQ2GRF2W3XTWDC/graph.json","fetch_events":"https://pith.science/api/pith-number/UXNGYAMW62CNOQ2GRF2W3XTWDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC/action/storage_attestation","attest_author":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC/action/author_attestation","sign_citation":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC/action/citation_signature","submit_replication":"https://pith.science/pith/UXNGYAMW62CNOQ2GRF2W3XTWDC/action/replication_record"}},"created_at":"2026-07-05T11:05:47.975610+00:00","updated_at":"2026-07-05T11:05:47.975610+00:00"}