{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YBZNBGIK4HGPUALUARVTIBUJ2F","short_pith_number":"pith:YBZNBGIK","schema_version":"1.0","canonical_sha256":"c072d0990ae1ccfa0174046b340689d148c43776adef0b679dd01d455f5a2ce6","source":{"kind":"arxiv","id":"2501.04302","version":1},"attestation_state":"computed","paper":{"title":"H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Siran Chen, Yali Wang, Yue Ma, Yu Qiao, Yuxiao Luo","submitted_at":"2025-01-08T06:26:16Z","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"},"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":"2501.04302","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T06:26:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d23024815ba06aa8ed8e0801121d19dcab081b6059b60f607e67e7797d54b10","abstract_canon_sha256":"d46285d792161b517bef4c7fd9847e38625e10882ab05fd6f9509a64f1fdae46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:33.043882Z","signature_b64":"z+g17xb7RvSb/xDTwmuD+AKzRYMWz7AJIZbR12D5Wa6wkKcwpxVBc7RtpR5LnWfLBffJFLJuQCI57m1QBW71Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c072d0990ae1ccfa0174046b340689d148c43776adef0b679dd01d455f5a2ce6","last_reissued_at":"2026-07-05T09:58:33.043430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:33.043430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Siran Chen, Yali Wang, Yue Ma, Yu Qiao, Yuxiao Luo","submitted_at":"2025-01-08T06:26:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04302","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/2501.04302/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":"2501.04302","created_at":"2026-07-05T09:58:33.043487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04302v1","created_at":"2026-07-05T09:58:33.043487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04302","created_at":"2026-07-05T09:58:33.043487+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBZNBGIK4HGP","created_at":"2026-07-05T09:58:33.043487+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBZNBGIK4HGPUALU","created_at":"2026-07-05T09:58:33.043487+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBZNBGIK","created_at":"2026-07-05T09:58:33.043487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19778","citing_title":"HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F","json":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F.json","graph_json":"https://pith.science/api/pith-number/YBZNBGIK4HGPUALUARVTIBUJ2F/graph.json","events_json":"https://pith.science/api/pith-number/YBZNBGIK4HGPUALUARVTIBUJ2F/events.json","paper":"https://pith.science/paper/YBZNBGIK"},"agent_actions":{"view_html":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F","download_json":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F.json","view_paper":"https://pith.science/paper/YBZNBGIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04302&json=true","fetch_graph":"https://pith.science/api/pith-number/YBZNBGIK4HGPUALUARVTIBUJ2F/graph.json","fetch_events":"https://pith.science/api/pith-number/YBZNBGIK4HGPUALUARVTIBUJ2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F/action/storage_attestation","attest_author":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F/action/author_attestation","sign_citation":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F/action/citation_signature","submit_replication":"https://pith.science/pith/YBZNBGIK4HGPUALUARVTIBUJ2F/action/replication_record"}},"created_at":"2026-07-05T09:58:33.043487+00:00","updated_at":"2026-07-05T09:58:33.043487+00:00"}