{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IBY5KFQYFYZAOC27YX327Z2PTU","short_pith_number":"pith:IBY5KFQY","schema_version":"1.0","canonical_sha256":"4071d516182e32070b5fc5f7afe74f9d2c31667f9f4c1c4cbeefa258a15e7911","source":{"kind":"arxiv","id":"2404.15014","version":1},"attestation_state":"computed","paper":{"title":"OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bailan Feng, Chao Ma, Guoqing Wang, Jilai Zheng, Pin Tang, Xiangxuan Ren, Zhongdao Wang","submitted_at":"2024-04-23T13:20:09Z","abstract_excerpt":"Existing solutions for 3D semantic occupancy prediction typically treat the task as a one-shot 3D voxel-wise segmentation perception problem. These discriminative methods focus on learning the mapping between the inputs and occupancy map in a single step, lacking the ability to gradually refine the occupancy map and the reasonable scene imaginative capacity to complete the local regions somewhere. In this paper, we introduce OccGen, a simple yet powerful generative perception model for the task of 3D semantic occupancy prediction. OccGen adopts a ''noise-to-occupancy'' generative paradigm, pro"},"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":"2404.15014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-23T13:20:09Z","cross_cats_sorted":[],"title_canon_sha256":"393c9ae2311ca4b9b5ecf1527cba53bdd5174ad68ecdea6728a8ac1d265113c8","abstract_canon_sha256":"732af21367d29143b50b707401ee1c175f475f2971ad0b306510749930e2e8d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:13.932636Z","signature_b64":"aRs1+x1xCGadtQqpRPpHHiGwwIjLTEBqlduTnKjx65Uf7Ju5FxVWcN69QBMIoxKS9FYIP9C54e+Xzo9wk2i+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4071d516182e32070b5fc5f7afe74f9d2c31667f9f4c1c4cbeefa258a15e7911","last_reissued_at":"2026-07-05T08:11:13.932136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:13.932136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OccGen: Generative Multi-modal 3D Occupancy Prediction for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bailan Feng, Chao Ma, Guoqing Wang, Jilai Zheng, Pin Tang, Xiangxuan Ren, Zhongdao Wang","submitted_at":"2024-04-23T13:20:09Z","abstract_excerpt":"Existing solutions for 3D semantic occupancy prediction typically treat the task as a one-shot 3D voxel-wise segmentation perception problem. These discriminative methods focus on learning the mapping between the inputs and occupancy map in a single step, lacking the ability to gradually refine the occupancy map and the reasonable scene imaginative capacity to complete the local regions somewhere. In this paper, we introduce OccGen, a simple yet powerful generative perception model for the task of 3D semantic occupancy prediction. OccGen adopts a ''noise-to-occupancy'' generative paradigm, pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15014","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/2404.15014/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":"2404.15014","created_at":"2026-07-05T08:11:13.932198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15014v1","created_at":"2026-07-05T08:11:13.932198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15014","created_at":"2026-07-05T08:11:13.932198+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBY5KFQYFYZA","created_at":"2026-07-05T08:11:13.932198+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBY5KFQYFYZAOC27","created_at":"2026-07-05T08:11:13.932198+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBY5KFQY","created_at":"2026-07-05T08:11:13.932198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17083","citing_title":"SDGOCC: Semantic and Depth-Guided Bird's-Eye View Transformation for 3D Multimodal Occupancy Prediction","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU","json":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU.json","graph_json":"https://pith.science/api/pith-number/IBY5KFQYFYZAOC27YX327Z2PTU/graph.json","events_json":"https://pith.science/api/pith-number/IBY5KFQYFYZAOC27YX327Z2PTU/events.json","paper":"https://pith.science/paper/IBY5KFQY"},"agent_actions":{"view_html":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU","download_json":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU.json","view_paper":"https://pith.science/paper/IBY5KFQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15014&json=true","fetch_graph":"https://pith.science/api/pith-number/IBY5KFQYFYZAOC27YX327Z2PTU/graph.json","fetch_events":"https://pith.science/api/pith-number/IBY5KFQYFYZAOC27YX327Z2PTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU/action/storage_attestation","attest_author":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU/action/author_attestation","sign_citation":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU/action/citation_signature","submit_replication":"https://pith.science/pith/IBY5KFQYFYZAOC27YX327Z2PTU/action/replication_record"}},"created_at":"2026-07-05T08:11:13.932198+00:00","updated_at":"2026-07-05T08:11:13.932198+00:00"}