{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XMM4ST4QYEJRON7OT7ZPT55K7Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bb63772c7d1fc4eee3c00d3ce56dfb7b848e02ea69be05ae2f2763227bcfec35","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T09:50:44Z","title_canon_sha256":"7fb2051baf24369be5ab8d1300c51bd26da29478cb5c26144268de24c8eb504c"},"schema_version":"1.0","source":{"id":"2502.14917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14917","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14917v1","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14917","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"pith_short_12","alias_value":"XMM4ST4QYEJR","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"pith_short_16","alias_value":"XMM4ST4QYEJRON7O","created_at":"2026-07-05T10:17:36Z"},{"alias_kind":"pith_short_8","alias_value":"XMM4ST4Q","created_at":"2026-07-05T10:17:36Z"}],"graph_snapshots":[{"event_id":"sha256:96435d76961645849f239d3acccfed9aa478fa21e11bc6dc8c4e165cf59957f9","target":"graph","created_at":"2026-07-05T10:17:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.14917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chengyuan Zheng, Fei Gao, Haofeng Hu, Jinyu Li, Qirui Yuan, Rui Zhao, Yun Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T09:50:44Z","title":"Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14917","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:edca992d243ac9d175fe7c54748721da94888518e7898808ed8935883a45d18d","target":"record","created_at":"2026-07-05T10:17:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bb63772c7d1fc4eee3c00d3ce56dfb7b848e02ea69be05ae2f2763227bcfec35","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-19T09:50:44Z","title_canon_sha256":"7fb2051baf24369be5ab8d1300c51bd26da29478cb5c26144268de24c8eb504c"},"schema_version":"1.0","source":{"id":"2502.14917","kind":"arxiv","version":1}},"canonical_sha256":"bb19c94f90c1131737ee9ff2f9f7aafe591c83d4f0d88599319526aad11123c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb19c94f90c1131737ee9ff2f9f7aafe591c83d4f0d88599319526aad11123c8","first_computed_at":"2026-07-05T10:17:36.247094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:36.247094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wM/95ncCEfui5tKrZyOMsbJjh62AHwZjpHvVkFu3+b0WQFhx2ZuGPAz9+gMSjNd+katJwUDOZFHGTjNwqIk7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:36.247563Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:edca992d243ac9d175fe7c54748721da94888518e7898808ed8935883a45d18d","sha256:96435d76961645849f239d3acccfed9aa478fa21e11bc6dc8c4e165cf59957f9"],"state_sha256":"73acddcaf28f5860e89b6160da1735c689be8e58e72ccee77516bc3628b85aa7"}