{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XMM4ST4QYEJRON7OT7ZPT55K7Z","short_pith_number":"pith:XMM4ST4Q","schema_version":"1.0","canonical_sha256":"bb19c94f90c1131737ee9ff2f9f7aafe591c83d4f0d88599319526aad11123c8","source":{"kind":"arxiv","id":"2502.14917","version":1},"attestation_state":"computed","paper":{"title":"Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengyuan Zheng, Fei Gao, Haofeng Hu, Jinyu Li, Qirui Yuan, Rui Zhao, Yun Li","submitted_at":"2025-02-19T09:50:44Z","abstract_excerpt":"End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an important part of Embodied AI. Despite successes in applying Multimodal Large Language Models (MLLMs) for high-level traffic scene semantic understanding, it remains challenging to effectively translate these conceptual semantics understandings into low-level motion control commands and achieve generalization and consensus in cross-scene driving. We introduce Sce2DriveX, a human-like driving chain-of-thought (CoT) reasoning MLLM framework. Sce2DriveX utilizes multimodal joint learning from"},"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":"2502.14917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T09:50:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7fb2051baf24369be5ab8d1300c51bd26da29478cb5c26144268de24c8eb504c","abstract_canon_sha256":"bb63772c7d1fc4eee3c00d3ce56dfb7b848e02ea69be05ae2f2763227bcfec35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:36.247563Z","signature_b64":"wM/95ncCEfui5tKrZyOMsbJjh62AHwZjpHvVkFu3+b0WQFhx2ZuGPAz9+gMSjNd+katJwUDOZFHGTjNwqIk7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb19c94f90c1131737ee9ff2f9f7aafe591c83d4f0d88599319526aad11123c8","last_reissued_at":"2026-07-05T10:17:36.247094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:36.247094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengyuan Zheng, Fei Gao, Haofeng Hu, Jinyu Li, Qirui Yuan, Rui Zhao, Yun Li","submitted_at":"2025-02-19T09:50:44Z","abstract_excerpt":"End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an important part of Embodied AI. Despite successes in applying Multimodal Large Language Models (MLLMs) for high-level traffic scene semantic understanding, it remains challenging to effectively translate these conceptual semantics understandings into low-level motion control commands and achieve generalization and consensus in cross-scene driving. We introduce Sce2DriveX, a human-like driving chain-of-thought (CoT) reasoning MLLM framework. Sce2DriveX utilizes multimodal joint learning from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14917","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/2502.14917/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":"2502.14917","created_at":"2026-07-05T10:17:36.247147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14917v1","created_at":"2026-07-05T10:17:36.247147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14917","created_at":"2026-07-05T10:17:36.247147+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMM4ST4QYEJR","created_at":"2026-07-05T10:17:36.247147+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMM4ST4QYEJRON7O","created_at":"2026-07-05T10:17:36.247147+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMM4ST4Q","created_at":"2026-07-05T10:17:36.247147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00399","citing_title":"DriveVer: Lightweight Trajectory Evaluator as Test-Time Verifier for Autonomous Driving","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01594","citing_title":"MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z","json":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z.json","graph_json":"https://pith.science/api/pith-number/XMM4ST4QYEJRON7OT7ZPT55K7Z/graph.json","events_json":"https://pith.science/api/pith-number/XMM4ST4QYEJRON7OT7ZPT55K7Z/events.json","paper":"https://pith.science/paper/XMM4ST4Q"},"agent_actions":{"view_html":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z","download_json":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z.json","view_paper":"https://pith.science/paper/XMM4ST4Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14917&json=true","fetch_graph":"https://pith.science/api/pith-number/XMM4ST4QYEJRON7OT7ZPT55K7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/XMM4ST4QYEJRON7OT7ZPT55K7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z/action/storage_attestation","attest_author":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z/action/author_attestation","sign_citation":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z/action/citation_signature","submit_replication":"https://pith.science/pith/XMM4ST4QYEJRON7OT7ZPT55K7Z/action/replication_record"}},"created_at":"2026-07-05T10:17:36.247147+00:00","updated_at":"2026-07-05T10:17:36.247147+00:00"}