{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RE72PZYAUT5BQIPFAQBYM6NYC2","short_pith_number":"pith:RE72PZYA","schema_version":"1.0","canonical_sha256":"893fa7e700a4fa1821e504038679b8169802da078e580bc582abd0cb9c7c66cf","source":{"kind":"arxiv","id":"2406.04339","version":2},"attestation_state":"computed","paper":{"title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaming Liu, Kaichen Zhou, Mengzhen Liu, Pengju An, Renrui Zhang, Senqiao Yang, Shanghang Zhang, Xiaoqi Li, Yandong Guo, Zhenyu Wang","submitted_at":"2024-06-06T17:59:47Z","abstract_excerpt":"A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face challenges in two areas: (1) insufficient reasoning ability to tackle complex tasks, and (2) high computational costs for VLA model fine-tuning and inference. The recently proposed state space model (SSM) known as Mamba demonstrates promising capabilities in non-trivial sequence modeling with linear inference complexity. Inspired by this, we introduce RoboMamba, an e"},"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":"2406.04339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-06T17:59:47Z","cross_cats_sorted":[],"title_canon_sha256":"28161fd009b177622e1da18f36fdd2d5acbfb2a57861378cc8df6a9f546b03e0","abstract_canon_sha256":"061161e0c3ec1c15414bca61ec9e6d6228aeba81626cb0a8b64a790d7cf762f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:06.065246Z","signature_b64":"qk5oua3vHwhtTKVKHsOqi+19PKAiJrw7gA9Wo2Q62AxdlX3CCzxzEWgUAoiXhyI/leD+Ex81DPgRhyu1FY34AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"893fa7e700a4fa1821e504038679b8169802da078e580bc582abd0cb9c7c66cf","last_reissued_at":"2026-07-05T09:49:06.064741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:06.064741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaming Liu, Kaichen Zhou, Mengzhen Liu, Pengju An, Renrui Zhang, Senqiao Yang, Shanghang Zhang, Xiaoqi Li, Yandong Guo, Zhenyu Wang","submitted_at":"2024-06-06T17:59:47Z","abstract_excerpt":"A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face challenges in two areas: (1) insufficient reasoning ability to tackle complex tasks, and (2) high computational costs for VLA model fine-tuning and inference. The recently proposed state space model (SSM) known as Mamba demonstrates promising capabilities in non-trivial sequence modeling with linear inference complexity. Inspired by this, we introduce RoboMamba, an e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04339","kind":"arxiv","version":2},"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/2406.04339/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":"2406.04339","created_at":"2026-07-05T09:49:06.064807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04339v2","created_at":"2026-07-05T09:49:06.064807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04339","created_at":"2026-07-05T09:49:06.064807+00:00"},{"alias_kind":"pith_short_12","alias_value":"RE72PZYAUT5B","created_at":"2026-07-05T09:49:06.064807+00:00"},{"alias_kind":"pith_short_16","alias_value":"RE72PZYAUT5BQIPF","created_at":"2026-07-05T09:49:06.064807+00:00"},{"alias_kind":"pith_short_8","alias_value":"RE72PZYA","created_at":"2026-07-05T09:49:06.064807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21854","citing_title":"CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31909","citing_title":"CoDex: Learning Compositional Dexterous Functional Manipulation without Demonstrations","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21854","citing_title":"CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14058","citing_title":"What Matters in Building Vision-Language-Action Models for Generalist Robots","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17573","citing_title":"HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24447","citing_title":"Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07935","citing_title":"The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07308","citing_title":"AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2","json":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2.json","graph_json":"https://pith.science/api/pith-number/RE72PZYAUT5BQIPFAQBYM6NYC2/graph.json","events_json":"https://pith.science/api/pith-number/RE72PZYAUT5BQIPFAQBYM6NYC2/events.json","paper":"https://pith.science/paper/RE72PZYA"},"agent_actions":{"view_html":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2","download_json":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2.json","view_paper":"https://pith.science/paper/RE72PZYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04339&json=true","fetch_graph":"https://pith.science/api/pith-number/RE72PZYAUT5BQIPFAQBYM6NYC2/graph.json","fetch_events":"https://pith.science/api/pith-number/RE72PZYAUT5BQIPFAQBYM6NYC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2/action/storage_attestation","attest_author":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2/action/author_attestation","sign_citation":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2/action/citation_signature","submit_replication":"https://pith.science/pith/RE72PZYAUT5BQIPFAQBYM6NYC2/action/replication_record"}},"created_at":"2026-07-05T09:49:06.064807+00:00","updated_at":"2026-07-05T09:49:06.064807+00:00"}