{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ERULEXM5DZT4ZDURXZ4D52MVOP","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":"fae3ab77afedf2d7c8cfb0c9bc673a653a43811eb680db355a9bfd0799b7e7ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T18:26:30Z","title_canon_sha256":"61dcdbdf221ed2cae1339c6d379a52a29893fbeb0e2942cb4bd90936ca9db68a"},"schema_version":"1.0","source":{"id":"2505.18819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18819","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18819v1","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18819","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_12","alias_value":"ERULEXM5DZT4","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_16","alias_value":"ERULEXM5DZT4ZDUR","created_at":"2026-07-05T11:09:20Z"},{"alias_kind":"pith_short_8","alias_value":"ERULEXM5","created_at":"2026-07-05T11:09:20Z"}],"graph_snapshots":[{"event_id":"sha256:92af4655c50ba4a93690789fbe0fdce819e854b5a53bcfb66ec5817c0ddb0f7b","target":"graph","created_at":"2026-07-05T11:09:20Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.18819/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models like CLIP can offer a promising foundation for 3D scene understanding when extended with 3D tokenizers. However, standard approaches, such as k-nearest neighbor or radius-based tokenization, struggle with cross-domain generalization due to sensitivity to dataset-specific spatial scales. We present a universal 3D tokenizer designed for scale-invariant representation learning with a frozen CLIP backbone. We show that combining superpoint-based grouping with coordinate scale normalization consistently outperforms conventional methods through extensive experimental analysis.","authors_text":"Bin Ren, Fabio Poiesi, Guofeng Mei, Juan Liu, Luigi Riz, Ming-Hsuan Yang, Nicu Sebe, Xiaoshui Huang, Xu Zheng, Yongshun Gong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T18:26:30Z","title":"Self-Supervised and Generalizable Tokenization for CLIP-Based 3D Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18819","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:32523096445cd96c4e44438ee2b11afaf923b762f120e155571a294c536f563e","target":"record","created_at":"2026-07-05T11:09:20Z","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":"fae3ab77afedf2d7c8cfb0c9bc673a653a43811eb680db355a9bfd0799b7e7ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T18:26:30Z","title_canon_sha256":"61dcdbdf221ed2cae1339c6d379a52a29893fbeb0e2942cb4bd90936ca9db68a"},"schema_version":"1.0","source":{"id":"2505.18819","kind":"arxiv","version":1}},"canonical_sha256":"2468b25d9d1e67cc8e91be783ee99573ec0dbd914a706c2a334acc10b84c8aaf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2468b25d9d1e67cc8e91be783ee99573ec0dbd914a706c2a334acc10b84c8aaf","first_computed_at":"2026-07-05T11:09:20.096887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:20.096887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YP6jmltIxqx9xxkW6wbgkXbLinsxnlLQgf61vcnscGlpq9ujn7/SdtyJcn05W2gTEgtuKDorAsqv8zir8DmlCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:20.097382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32523096445cd96c4e44438ee2b11afaf923b762f120e155571a294c536f563e","sha256:92af4655c50ba4a93690789fbe0fdce819e854b5a53bcfb66ec5817c0ddb0f7b"],"state_sha256":"a45afca9a9323f93a7b0aaf60c88b1098c3aa3f36dd414058797c30d400c0721"}