{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QWGPQRXCE4INVVTPJY2WLLTHTU","short_pith_number":"pith:QWGPQRXC","schema_version":"1.0","canonical_sha256":"858cf846e22710dad66f4e3565ae679d09c8b607b731f86c5a8dfbd4a6d809cc","source":{"kind":"arxiv","id":"2412.04384","version":2},"attestation_state":"computed","paper":{"title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amonnut Thammatadatrakoon, Dalong Du, Jiwen Lu, Wenzhao Zheng, Yuanhui Huang, Yunpeng Zhang","submitted_at":"2024-12-05T17:59:58Z","abstract_excerpt":"3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. Although 3D semantic Gaussian serves as an object-centric sparse alternative, most of the Gaussians still describe the empty region with low efficiency. To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its ne"},"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":"2412.04384","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T17:59:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"81583ce4d1b9303f8b11c44381f28f1a712bbbf144a84720d3f870b29fc89a19","abstract_canon_sha256":"2f69f0cf0d1ac35184054c1c3004a11c355dcd584bdbecb9ea05db51ac5c6231"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:17.900106Z","signature_b64":"AoeKj3Unze8djS1lo81PbZg84dvWvLKggh7rY9BOUf6nxnM0hJPRS0VeqVLpPNwp5jbJiGh+2EKSI1Rq8VruBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"858cf846e22710dad66f4e3565ae679d09c8b607b731f86c5a8dfbd4a6d809cc","last_reissued_at":"2026-07-05T09:45:17.899630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:17.899630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amonnut Thammatadatrakoon, Dalong Du, Jiwen Lu, Wenzhao Zheng, Yuanhui Huang, Yunpeng Zhang","submitted_at":"2024-12-05T17:59:58Z","abstract_excerpt":"3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. Although 3D semantic Gaussian serves as an object-centric sparse alternative, most of the Gaussians still describe the empty region with low efficiency. To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04384","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/2412.04384/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":"2412.04384","created_at":"2026-07-05T09:45:17.899684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04384v2","created_at":"2026-07-05T09:45:17.899684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04384","created_at":"2026-07-05T09:45:17.899684+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWGPQRXCE4IN","created_at":"2026-07-05T09:45:17.899684+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWGPQRXCE4INVVTP","created_at":"2026-07-05T09:45:17.899684+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWGPQRXC","created_at":"2026-07-05T09:45:17.899684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13460","citing_title":"VISA: VLM-Guided Instance Semantic Auditing for 3D Occupancy World Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22667","citing_title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU","json":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU.json","graph_json":"https://pith.science/api/pith-number/QWGPQRXCE4INVVTPJY2WLLTHTU/graph.json","events_json":"https://pith.science/api/pith-number/QWGPQRXCE4INVVTPJY2WLLTHTU/events.json","paper":"https://pith.science/paper/QWGPQRXC"},"agent_actions":{"view_html":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU","download_json":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU.json","view_paper":"https://pith.science/paper/QWGPQRXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04384&json=true","fetch_graph":"https://pith.science/api/pith-number/QWGPQRXCE4INVVTPJY2WLLTHTU/graph.json","fetch_events":"https://pith.science/api/pith-number/QWGPQRXCE4INVVTPJY2WLLTHTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU/action/storage_attestation","attest_author":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU/action/author_attestation","sign_citation":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU/action/citation_signature","submit_replication":"https://pith.science/pith/QWGPQRXCE4INVVTPJY2WLLTHTU/action/replication_record"}},"created_at":"2026-07-05T09:45:17.899684+00:00","updated_at":"2026-07-05T09:45:17.899684+00:00"}