{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PEMB5FJXACXPRHERASBMC43VN6","short_pith_number":"pith:PEMB5FJX","schema_version":"1.0","canonical_sha256":"79181e953700aef89c910482c173756f87e9becc8a19a05f50561772bef8598e","source":{"kind":"arxiv","id":"2503.11122","version":1},"attestation_state":"computed","paper":{"title":"DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbin Lin, Ruimao Zhang, Shuaicheng Niu, Shuguang Cui, Yafeng Li, Yifan Zhang, Zhen Li, Zilu Guo","submitted_at":"2025-03-14T06:35:38Z","abstract_excerpt":"In autonomous driving, vision-centric 3D detection aims to identify 3D objects from images. However, high data collection costs and diverse real-world scenarios limit the scale of training data. Once distribution shifts occur between training and test data, existing methods often suffer from performance degradation, known as Out-of-Distribution (OOD) problems. To address this, controllable Text-to-Image (T2I) diffusion offers a potential solution for training data enhancement, which is required to generate diverse OOD scenarios with precise 3D object geometry. Nevertheless, existing controllab"},"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":"2503.11122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T06:35:38Z","cross_cats_sorted":[],"title_canon_sha256":"36d9342218fe77228d0b2825229296571445a736e64dc1936c680a5bb940f38c","abstract_canon_sha256":"1fa3b1a37e296ab36fec15367af99454051162a5bb5227fbed598f53be38b467"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:12.330743Z","signature_b64":"JpjAVKVFA5VSohI1CE+4lhfVw8BXuxbld1E7+fFAze1t9l3tFoNDUzZbOAJlG2ZCMaej+0IRPtesTOs57VCEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79181e953700aef89c910482c173756f87e9becc8a19a05f50561772bef8598e","last_reissued_at":"2026-07-05T10:31:12.330235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:12.330235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DriveGEN: Generalized and Robust 3D Detection in Driving via Controllable Text-to-Image Diffusion Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongbin Lin, Ruimao Zhang, Shuaicheng Niu, Shuguang Cui, Yafeng Li, Yifan Zhang, Zhen Li, Zilu Guo","submitted_at":"2025-03-14T06:35:38Z","abstract_excerpt":"In autonomous driving, vision-centric 3D detection aims to identify 3D objects from images. However, high data collection costs and diverse real-world scenarios limit the scale of training data. Once distribution shifts occur between training and test data, existing methods often suffer from performance degradation, known as Out-of-Distribution (OOD) problems. To address this, controllable Text-to-Image (T2I) diffusion offers a potential solution for training data enhancement, which is required to generate diverse OOD scenarios with precise 3D object geometry. Nevertheless, existing controllab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11122","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/2503.11122/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":"2503.11122","created_at":"2026-07-05T10:31:12.330289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11122v1","created_at":"2026-07-05T10:31:12.330289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11122","created_at":"2026-07-05T10:31:12.330289+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEMB5FJXACXP","created_at":"2026-07-05T10:31:12.330289+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEMB5FJXACXPRHER","created_at":"2026-07-05T10:31:12.330289+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEMB5FJX","created_at":"2026-07-05T10:31:12.330289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.15422","citing_title":"A Survey on the Applications of Generative Artificial Intelligence in Automated Driving Systems Test Scenario Generation Methods","ref_index":87,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6","json":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6.json","graph_json":"https://pith.science/api/pith-number/PEMB5FJXACXPRHERASBMC43VN6/graph.json","events_json":"https://pith.science/api/pith-number/PEMB5FJXACXPRHERASBMC43VN6/events.json","paper":"https://pith.science/paper/PEMB5FJX"},"agent_actions":{"view_html":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6","download_json":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6.json","view_paper":"https://pith.science/paper/PEMB5FJX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11122&json=true","fetch_graph":"https://pith.science/api/pith-number/PEMB5FJXACXPRHERASBMC43VN6/graph.json","fetch_events":"https://pith.science/api/pith-number/PEMB5FJXACXPRHERASBMC43VN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6/action/storage_attestation","attest_author":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6/action/author_attestation","sign_citation":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6/action/citation_signature","submit_replication":"https://pith.science/pith/PEMB5FJXACXPRHERASBMC43VN6/action/replication_record"}},"created_at":"2026-07-05T10:31:12.330289+00:00","updated_at":"2026-07-05T10:31:12.330289+00:00"}