{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LRKOQ5NJDOICRD2RPQTPHWU642","short_pith_number":"pith:LRKOQ5NJ","schema_version":"1.0","canonical_sha256":"5c54e875a91b90288f517c26f3da9ee685d4264f289eec240031b7aa95db23b1","source":{"kind":"arxiv","id":"2511.18112","version":3},"attestation_state":"computed","paper":{"title":"EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingqian Lin, Jiarui Hu, Jingzhi Liu, Kehan Li, Min Lin, Shen Zhao, Weijia Liufu, Xiaodan Liang, Xiwen Liang, Yuecheng Liu, Yuhan Ma, Yu Sun, Yuzheng Zhuang, Ziang Yan, Zijian Jiao","submitted_at":"2025-11-22T16:30:55Z","abstract_excerpt":"Recent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. However, existing VLAs are mostly confined to short-horizon, table-top manipulation, lacking the memory and reasoning capability required for mobile manipulation, where agents must coordinate navigation and manipulation under changing spatial contexts. In this work, we present EchoVLA, a memory-aware VLA model for mobile manipulation. EchoVLA incorporates a synergistic declarative memory inspired by the human brain, consisting of a scene memory that"},"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":"2511.18112","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-22T16:30:55Z","cross_cats_sorted":[],"title_canon_sha256":"d521757a212c080835fffd782ece0c7d5822a1db5c756f464cbe1c2f91eff58e","abstract_canon_sha256":"a90f0808f8a1af8d71fc901d1613b2cba713108be383bc62819e1aed53629221"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:09:23.023044Z","signature_b64":"4nf1i5HV97vrYbiuvac6U8ZjgMFJMvgiaDUaf0hmD8S+Z41FSPamEobY9jwa9qXMcA4qHfEiszpMfWFX6z1HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c54e875a91b90288f517c26f3da9ee685d4264f289eec240031b7aa95db23b1","last_reissued_at":"2026-08-10T01:09:23.020476Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:09:23.020476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoVLA: Robotic Vision-Language-Action Model with Synergistic Declarative Memory for Mobile Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bingqian Lin, Jiarui Hu, Jingzhi Liu, Kehan Li, Min Lin, Shen Zhao, Weijia Liufu, Xiaodan Liang, Xiwen Liang, Yuecheng Liu, Yuhan Ma, Yu Sun, Yuzheng Zhuang, Ziang Yan, Zijian Jiao","submitted_at":"2025-11-22T16:30:55Z","abstract_excerpt":"Recent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. However, existing VLAs are mostly confined to short-horizon, table-top manipulation, lacking the memory and reasoning capability required for mobile manipulation, where agents must coordinate navigation and manipulation under changing spatial contexts. In this work, we present EchoVLA, a memory-aware VLA model for mobile manipulation. EchoVLA incorporates a synergistic declarative memory inspired by the human brain, consisting of a scene memory that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.18112","kind":"arxiv","version":3},"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/2511.18112/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":"2511.18112","created_at":"2026-08-10T01:09:23.021453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.18112v3","created_at":"2026-08-10T01:09:23.021453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18112","created_at":"2026-08-10T01:09:23.021453+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRKOQ5NJDOIC","created_at":"2026-08-10T01:09:23.021453+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRKOQ5NJDOICRD2R","created_at":"2026-08-10T01:09:23.021453+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRKOQ5NJ","created_at":"2026-08-10T01:09:23.021453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":15,"sample":[{"citing_arxiv_id":"2606.21188","citing_title":"Remember what you did?: Learning Behavioral Memories for Partially Observable Object Manipulation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20092","citing_title":"EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.14551","citing_title":"TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12956","citing_title":"SERF: Spatiotemporal Environment and Robot Feature Map for Long-Horizon Mobile Manipulation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12499","citing_title":"Action-Effect Memory Pretraining for Robot Manipulation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12105","citing_title":"DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12497","citing_title":"$\\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.03787","citing_title":"Worth Remembering: Surprise-Gated Robot Episodic Memory","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20092","citing_title":"EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2601.07060","citing_title":"PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02525","citing_title":"A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18933","citing_title":"Gated Memory Policy: In-Context Memorization and Adaptation","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15023","citing_title":"DockAnywhere: Data-Efficient Visuomotor Policy Learning for Mobile Manipulation via Novel Demonstration Generation","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642","json":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642.json","graph_json":"https://pith.science/api/pith-number/LRKOQ5NJDOICRD2RPQTPHWU642/graph.json","events_json":"https://pith.science/api/pith-number/LRKOQ5NJDOICRD2RPQTPHWU642/events.json","paper":"https://pith.science/paper/LRKOQ5NJ"},"agent_actions":{"view_html":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642","download_json":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642.json","view_paper":"https://pith.science/paper/LRKOQ5NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.18112&json=true","fetch_graph":"https://pith.science/api/pith-number/LRKOQ5NJDOICRD2RPQTPHWU642/graph.json","fetch_events":"https://pith.science/api/pith-number/LRKOQ5NJDOICRD2RPQTPHWU642/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642/action/storage_attestation","attest_author":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642/action/author_attestation","sign_citation":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642/action/citation_signature","submit_replication":"https://pith.science/pith/LRKOQ5NJDOICRD2RPQTPHWU642/action/replication_record"}},"created_at":"2026-08-10T01:09:23.021453+00:00","updated_at":"2026-08-10T01:09:23.021453+00:00"}