{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U7FI6JM357HD56DHFDF34R4JPB","short_pith_number":"pith:U7FI6JM3","schema_version":"1.0","canonical_sha256":"a7ca8f259befce3ef86728cbbe47897854e93d8f0b94c5071719cfb8e71de077","source":{"kind":"arxiv","id":"2602.23172","version":2},"attestation_state":"computed","paper":{"title":"Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhinav Valada, Daniele Cattaneo, Maximilian Luz, Rohit Mohan, Thomas N\\\"urnberg, Yakov Miron","submitted_at":"2026-02-26T16:34:49Z","abstract_excerpt":"Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only part of the problem: they either provide coarse geometric tracking via bounding boxes or detailed 3D occupancy estimates that lack explicit temporal association and instance-level reasoning. In this work, we present Latent Gaussian Splatting (LaGS) for 4D Panoptic Occupancy Tracking (4D-POT). We revisit the underlying representation and model 3D features as a sparse set of feature-bearing Gaussians. These act as dynami"},"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":"2602.23172","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T16:34:49Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"7272ec27b5ca1c7fb583244753539d9a3244312acb4bda630f07fcafb46bb6bb","abstract_canon_sha256":"eb06c5c0282179e933102c18a6f01ab00ee4cc3a4cfe909a1aa2e7ed37e1ab4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:51.734463Z","signature_b64":"rg/C9ZjraelS+5BkFihMG8wXNPD4mckVPORbwbSn90c5znEf4o43HyJ/qZ5S0a9JSyQ5/CTn31NaBs9UVUSPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7ca8f259befce3ef86728cbbe47897854e93d8f0b94c5071719cfb8e71de077","last_reissued_at":"2026-06-19T16:12:51.733948Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:51.733948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Abhinav Valada, Daniele Cattaneo, Maximilian Luz, Rohit Mohan, Thomas N\\\"urnberg, Yakov Miron","submitted_at":"2026-02-26T16:34:49Z","abstract_excerpt":"Capturing 4D spatiotemporal scene structure is crucial for the safe and reliable operation of robots in dynamic environments. However, existing approaches typically address only part of the problem: they either provide coarse geometric tracking via bounding boxes or detailed 3D occupancy estimates that lack explicit temporal association and instance-level reasoning. In this work, we present Latent Gaussian Splatting (LaGS) for 4D Panoptic Occupancy Tracking (4D-POT). We revisit the underlying representation and model 3D features as a sparse set of feature-bearing Gaussians. These act as dynami"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.23172","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/2602.23172/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":"2602.23172","created_at":"2026-06-19T16:12:51.734017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.23172v2","created_at":"2026-06-19T16:12:51.734017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.23172","created_at":"2026-06-19T16:12:51.734017+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7FI6JM357HD","created_at":"2026-06-19T16:12:51.734017+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7FI6JM357HD56DH","created_at":"2026-06-19T16:12:51.734017+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7FI6JM3","created_at":"2026-06-19T16:12:51.734017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.30754","citing_title":"Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02580","citing_title":"Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings for Open-Set Panoptic Segmentation","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB","json":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB.json","graph_json":"https://pith.science/api/pith-number/U7FI6JM357HD56DHFDF34R4JPB/graph.json","events_json":"https://pith.science/api/pith-number/U7FI6JM357HD56DHFDF34R4JPB/events.json","paper":"https://pith.science/paper/U7FI6JM3"},"agent_actions":{"view_html":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB","download_json":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB.json","view_paper":"https://pith.science/paper/U7FI6JM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.23172&json=true","fetch_graph":"https://pith.science/api/pith-number/U7FI6JM357HD56DHFDF34R4JPB/graph.json","fetch_events":"https://pith.science/api/pith-number/U7FI6JM357HD56DHFDF34R4JPB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB/action/storage_attestation","attest_author":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB/action/author_attestation","sign_citation":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB/action/citation_signature","submit_replication":"https://pith.science/pith/U7FI6JM357HD56DHFDF34R4JPB/action/replication_record"}},"created_at":"2026-06-19T16:12:51.734017+00:00","updated_at":"2026-06-19T16:12:51.734017+00:00"}