{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJNW47AQNCW2PAODVZELHP2FQL","short_pith_number":"pith:ZJNW47AQ","schema_version":"1.0","canonical_sha256":"ca5b6e7c1068ada781c3ae48b3bf4582c6be4997a7b7f329e16a007e50b1941c","source":{"kind":"arxiv","id":"2505.18198","version":1},"attestation_state":"computed","paper":{"title":"LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhirup Mallik, Burhaneddin Yaman, Jingru Luo, John Pauly, Liu Ren, Mahmut Yurt, Xin Ye, Yunsheng Ma","submitted_at":"2025-05-21T05:14:11Z","abstract_excerpt":"3D perception plays an essential role for improving the safety and performance of autonomous driving. Yet, existing models trained on real-world datasets, which naturally exhibit long-tail distributions, tend to underperform on rare and safety-critical, vulnerable classes, such as pedestrians and cyclists. Existing studies on reweighting and resampling techniques struggle with the scarcity and limited diversity within tail classes. To address these limitations, we introduce LTDA-Drive, a novel LLM-guided data augmentation framework designed to synthesize diverse, high-quality long-tail samples"},"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":"2505.18198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-21T05:14:11Z","cross_cats_sorted":[],"title_canon_sha256":"86744c400895839cd0f6c106447834ccd1e922e1bddfd0b6fadc6d3e2b43cc34","abstract_canon_sha256":"c37eb71cced3692d5fe0fd4fad9857430fad716c4f79889308afb20ea170c82d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:42.696076Z","signature_b64":"xuK95s/XBgflEguKPF91jfUFkyUG+OQyV7MJMFa3obaAC570nDAeQZp07te7OVK3S68yGKHIvdFziWl+aWtaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca5b6e7c1068ada781c3ae48b3bf4582c6be4997a7b7f329e16a007e50b1941c","last_reissued_at":"2026-07-05T11:08:42.695551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:42.695551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LTDA-Drive: LLMs-guided Generative Models based Long-tail Data Augmentation for Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abhirup Mallik, Burhaneddin Yaman, Jingru Luo, John Pauly, Liu Ren, Mahmut Yurt, Xin Ye, Yunsheng Ma","submitted_at":"2025-05-21T05:14:11Z","abstract_excerpt":"3D perception plays an essential role for improving the safety and performance of autonomous driving. Yet, existing models trained on real-world datasets, which naturally exhibit long-tail distributions, tend to underperform on rare and safety-critical, vulnerable classes, such as pedestrians and cyclists. Existing studies on reweighting and resampling techniques struggle with the scarcity and limited diversity within tail classes. To address these limitations, we introduce LTDA-Drive, a novel LLM-guided data augmentation framework designed to synthesize diverse, high-quality long-tail samples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18198","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/2505.18198/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":"2505.18198","created_at":"2026-07-05T11:08:42.695619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18198v1","created_at":"2026-07-05T11:08:42.695619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18198","created_at":"2026-07-05T11:08:42.695619+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJNW47AQNCW2","created_at":"2026-07-05T11:08:42.695619+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJNW47AQNCW2PAOD","created_at":"2026-07-05T11:08:42.695619+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJNW47AQ","created_at":"2026-07-05T11:08:42.695619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL","json":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL.json","graph_json":"https://pith.science/api/pith-number/ZJNW47AQNCW2PAODVZELHP2FQL/graph.json","events_json":"https://pith.science/api/pith-number/ZJNW47AQNCW2PAODVZELHP2FQL/events.json","paper":"https://pith.science/paper/ZJNW47AQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL","download_json":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL.json","view_paper":"https://pith.science/paper/ZJNW47AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18198&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJNW47AQNCW2PAODVZELHP2FQL/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJNW47AQNCW2PAODVZELHP2FQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL/action/storage_attestation","attest_author":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL/action/author_attestation","sign_citation":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL/action/citation_signature","submit_replication":"https://pith.science/pith/ZJNW47AQNCW2PAODVZELHP2FQL/action/replication_record"}},"created_at":"2026-07-05T11:08:42.695619+00:00","updated_at":"2026-07-05T11:08:42.695619+00:00"}