{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RTI3NOP67KPYRKFCLXDB5EKFBM","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":"0653b67562c0b970341239396d0815b1c3c2c2006ed6d1c9a8c29e7f39059502","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T06:49:17Z","title_canon_sha256":"e4a951c0fecd403f73a34dacd58e301e6284037423cae68587875ab20287da8b"},"schema_version":"1.0","source":{"id":"2607.00514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00514","created_at":"2026-07-02T01:17:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00514v1","created_at":"2026-07-02T01:17:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00514","created_at":"2026-07-02T01:17:46Z"},{"alias_kind":"pith_short_12","alias_value":"RTI3NOP67KPY","created_at":"2026-07-02T01:17:46Z"},{"alias_kind":"pith_short_16","alias_value":"RTI3NOP67KPYRKFC","created_at":"2026-07-02T01:17:46Z"},{"alias_kind":"pith_short_8","alias_value":"RTI3NOP6","created_at":"2026-07-02T01:17:46Z"}],"graph_snapshots":[{"event_id":"sha256:42c13f8913ec6ae08778c056ea1eb71c925b0b49adb59e0bba55a26eb8eb87f2","target":"graph","created_at":"2026-07-02T01:17:46Z","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/2607.00514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hai Nguyen-Truong, Hoang M. Truong, Trung Thanh Nguyen, Tuan-Anh Vu, Tu Vo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T06:49:17Z","title":"Cross4D-JEPA: Dense Cross-modal Correspondence Distillation for 4D Point Cloud Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00514","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":"sha256:0066a553ec9fa8d48c7123a478b1df49182b458f744834d770400f4a22944089","target":"record","created_at":"2026-07-02T01:17:46Z","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":"0653b67562c0b970341239396d0815b1c3c2c2006ed6d1c9a8c29e7f39059502","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T06:49:17Z","title_canon_sha256":"e4a951c0fecd403f73a34dacd58e301e6284037423cae68587875ab20287da8b"},"schema_version":"1.0","source":{"id":"2607.00514","kind":"arxiv","version":1}},"canonical_sha256":"8cd1b6b9fefa9f88a8a25dc61e91450b2ad6b0de06e6a11858abdb683d267e54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cd1b6b9fefa9f88a8a25dc61e91450b2ad6b0de06e6a11858abdb683d267e54","first_computed_at":"2026-07-02T01:17:46.395081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:17:46.395081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15cmQfWo93+/zTWcduDXWdBbWiqB8pgzc9SEkl3nQ3zGpvfdFj3ZhtrhDiVBNEnz2OzW1pS9Ic6bshrWt6WoAA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:17:46.395475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0066a553ec9fa8d48c7123a478b1df49182b458f744834d770400f4a22944089","sha256:42c13f8913ec6ae08778c056ea1eb71c925b0b49adb59e0bba55a26eb8eb87f2"],"state_sha256":"943bed40864c8e817ecb75c0360bb222afd3062b6c860996dbe5755aaa9fe582"}