{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RTI3NOP67KPYRKFCLXDB5EKFBM","short_pith_number":"pith:RTI3NOP6","schema_version":"1.0","canonical_sha256":"8cd1b6b9fefa9f88a8a25dc61e91450b2ad6b0de06e6a11858abdb683d267e54","source":{"kind":"arxiv","id":"2607.00514","version":1},"attestation_state":"computed","paper":{"title":"Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hai Nguyen-Truong, Hoang M. Truong, Trung Thanh Nguyen, Tuan-Anh Vu, Tu Vo","submitted_at":"2026-07-01T06:49:17Z","abstract_excerpt":"Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception. Yet annotating them densely is expensive, making self-supervised pretraining the natural route to transferable representations. Existing pretext tasks, however, are almost entirely intra-modal, and the few methods that transfer knowledge from 2D foundation models rely on a single global embedding per clip, discarding the rich per-patch semantics that these models compute. To address this gap, we propose Cross4D-JEPA, a teacher"},"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":"2607.00514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T06:49:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e4a951c0fecd403f73a34dacd58e301e6284037423cae68587875ab20287da8b","abstract_canon_sha256":"0653b67562c0b970341239396d0815b1c3c2c2006ed6d1c9a8c29e7f39059502"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:46.395475Z","signature_b64":"15cmQfWo93+/zTWcduDXWdBbWiqB8pgzc9SEkl3nQ3zGpvfdFj3ZhtrhDiVBNEnz2OzW1pS9Ic6bshrWt6WoAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cd1b6b9fefa9f88a8a25dc61e91450b2ad6b0de06e6a11858abdb683d267e54","last_reissued_at":"2026-07-02T01:17:46.395081Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:46.395081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hai Nguyen-Truong, Hoang M. Truong, Trung Thanh Nguyen, Tuan-Anh Vu, Tu Vo","submitted_at":"2026-07-01T06:49:17Z","abstract_excerpt":"Automatic understanding of dynamic 4D point clouds, the 3D-point sequences captured over time by depth sensors and LiDAR, is central to robotics and embodied perception. Yet annotating them densely is expensive, making self-supervised pretraining the natural route to transferable representations. Existing pretext tasks, however, are almost entirely intra-modal, and the few methods that transfer knowledge from 2D foundation models rely on a single global embedding per clip, discarding the rich per-patch semantics that these models compute. To address this gap, we propose Cross4D-JEPA, a teacher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00514","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/2607.00514/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":"2607.00514","created_at":"2026-07-02T01:17:46.395139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00514v1","created_at":"2026-07-02T01:17:46.395139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00514","created_at":"2026-07-02T01:17:46.395139+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTI3NOP67KPY","created_at":"2026-07-02T01:17:46.395139+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTI3NOP67KPYRKFC","created_at":"2026-07-02T01:17:46.395139+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTI3NOP6","created_at":"2026-07-02T01:17:46.395139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM","json":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM.json","graph_json":"https://pith.science/api/pith-number/RTI3NOP67KPYRKFCLXDB5EKFBM/graph.json","events_json":"https://pith.science/api/pith-number/RTI3NOP67KPYRKFCLXDB5EKFBM/events.json","paper":"https://pith.science/paper/RTI3NOP6"},"agent_actions":{"view_html":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM","download_json":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM.json","view_paper":"https://pith.science/paper/RTI3NOP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00514&json=true","fetch_graph":"https://pith.science/api/pith-number/RTI3NOP67KPYRKFCLXDB5EKFBM/graph.json","fetch_events":"https://pith.science/api/pith-number/RTI3NOP67KPYRKFCLXDB5EKFBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM/action/storage_attestation","attest_author":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM/action/author_attestation","sign_citation":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM/action/citation_signature","submit_replication":"https://pith.science/pith/RTI3NOP67KPYRKFCLXDB5EKFBM/action/replication_record"}},"created_at":"2026-07-02T01:17:46.395139+00:00","updated_at":"2026-07-02T01:17:46.395139+00:00"}