{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBZNBGIK4HGPUALUARVTIBUJ2F","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":"d46285d792161b517bef4c7fd9847e38625e10882ab05fd6f9509a64f1fdae46","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T06:26:16Z","title_canon_sha256":"2d23024815ba06aa8ed8e0801121d19dcab081b6059b60f607e67e7797d54b10"},"schema_version":"1.0","source":{"id":"2501.04302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04302","created_at":"2026-07-05T09:58:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04302v1","created_at":"2026-07-05T09:58:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04302","created_at":"2026-07-05T09:58:33Z"},{"alias_kind":"pith_short_12","alias_value":"YBZNBGIK4HGP","created_at":"2026-07-05T09:58:33Z"},{"alias_kind":"pith_short_16","alias_value":"YBZNBGIK4HGPUALU","created_at":"2026-07-05T09:58:33Z"},{"alias_kind":"pith_short_8","alias_value":"YBZNBGIK","created_at":"2026-07-05T09:58:33Z"}],"graph_snapshots":[{"event_id":"sha256:7fe841d675fca3acefff235ebe6f014455b7281a95a9cd9b43d833ff8a08e6d6","target":"graph","created_at":"2026-07-05T09:58:33Z","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/2501.04302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the prevalence of Multimodal Large Language Models(MLLMs), autonomous driving has encountered new opportunities and challenges. In particular, multi-modal video understanding is critical to interactively analyze what will happen in the procedure of autonomous driving. However, videos in such a dynamical scene that often contains complex spatial-temporal movements, which restricts the generalization capacity of the existing MLLMs in this field. To bridge the gap, we propose a novel Hierarchical Mamba Adaptation (H-MBA) framework to fit the complicated motion changes in autonomous driving v","authors_text":"Siran Chen, Yali Wang, Yue Ma, Yu Qiao, Yuxiao Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T06:26:16Z","title":"H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04302","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":"sha256:268203193c43cf3feab05c77322fdf6a8151e2c441b0e6bca1b26c481aa5c648","target":"record","created_at":"2026-07-05T09:58:33Z","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":"d46285d792161b517bef4c7fd9847e38625e10882ab05fd6f9509a64f1fdae46","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T06:26:16Z","title_canon_sha256":"2d23024815ba06aa8ed8e0801121d19dcab081b6059b60f607e67e7797d54b10"},"schema_version":"1.0","source":{"id":"2501.04302","kind":"arxiv","version":1}},"canonical_sha256":"c072d0990ae1ccfa0174046b340689d148c43776adef0b679dd01d455f5a2ce6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c072d0990ae1ccfa0174046b340689d148c43776adef0b679dd01d455f5a2ce6","first_computed_at":"2026-07-05T09:58:33.043430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:33.043430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z+g17xb7RvSb/xDTwmuD+AKzRYMWz7AJIZbR12D5Wa6wkKcwpxVBc7RtpR5LnWfLBffJFLJuQCI57m1QBW71Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:33.043882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:268203193c43cf3feab05c77322fdf6a8151e2c441b0e6bca1b26c481aa5c648","sha256:7fe841d675fca3acefff235ebe6f014455b7281a95a9cd9b43d833ff8a08e6d6"],"state_sha256":"64fdd2e1c2f6a70a34e80007f14654bd1737601e54895a325d357eed9366b5b1"}