{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N7MKYG4N4GETMHDK6GUXX4PPF3","short_pith_number":"pith:N7MKYG4N","schema_version":"1.0","canonical_sha256":"6fd8ac1b8de189361c6af1a97bf1ef2ec0bd33c5c37bfcb8dd03b638ffdcf93e","source":{"kind":"arxiv","id":"2512.05693","version":2},"attestation_state":"computed","paper":{"title":"HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bei Liu, Haidong Cao, Jiaolong Yang, Xiangyu Zheng, Yaobo Liang, Yichao Shen, Yu-Gang Jiang, Zhiying Du, Zhiyuan Feng, Zuxuan Wu","submitted_at":"2025-12-05T13:21:05Z","abstract_excerpt":"Generalist vision--language--action (VLA) policies are typically trained on heterogeneous mixtures of robot demonstrations spanning diverse embodiments, action spaces, and observation configurations. Modeling such heterogeneity with a shared dense action module can induce negative transfer, particularly when action spaces or visual observations differ across data sources. We address this issue with HiMoE-VLA, a VLA framework built around a Hierarchical Mixture-of-Experts (HiMoE) action module. HiMoE uses Action-Space MoE layers at the input/output boundaries to specialize computation for disti"},"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":"2512.05693","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-12-05T13:21:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9416597de453f587bb874e22c57cee8f0c1eb5058a4587fda8887982007f2377","abstract_canon_sha256":"758cb2af04fe4b2f8959158be745946c7cf8d1363394f320f83e552d8d08b714"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:19:49.621679Z","signature_b64":"8E78xbW+WJ2InUqL4GjR1Kf1XhqR9x5izsfP/yqvvsQM+10+KECTrLjH3bpQbg9Mas0az5MW0RovCykH1NUdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fd8ac1b8de189361c6af1a97bf1ef2ec0bd33c5c37bfcb8dd03b638ffdcf93e","last_reissued_at":"2026-07-09T01:19:49.621188Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:19:49.621188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiMoE-VLA: Hierarchical Mixture-of-Experts for Generalist Vision-Language-Action Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bei Liu, Haidong Cao, Jiaolong Yang, Xiangyu Zheng, Yaobo Liang, Yichao Shen, Yu-Gang Jiang, Zhiying Du, Zhiyuan Feng, Zuxuan Wu","submitted_at":"2025-12-05T13:21:05Z","abstract_excerpt":"Generalist vision--language--action (VLA) policies are typically trained on heterogeneous mixtures of robot demonstrations spanning diverse embodiments, action spaces, and observation configurations. Modeling such heterogeneity with a shared dense action module can induce negative transfer, particularly when action spaces or visual observations differ across data sources. We address this issue with HiMoE-VLA, a VLA framework built around a Hierarchical Mixture-of-Experts (HiMoE) action module. HiMoE uses Action-Space MoE layers at the input/output boundaries to specialize computation for disti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.05693","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/2512.05693/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":"2512.05693","created_at":"2026-07-09T01:19:49.621242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.05693v2","created_at":"2026-07-09T01:19:49.621242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.05693","created_at":"2026-07-09T01:19:49.621242+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7MKYG4N4GET","created_at":"2026-07-09T01:19:49.621242+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7MKYG4N4GETMHDK","created_at":"2026-07-09T01:19:49.621242+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7MKYG4N","created_at":"2026-07-09T01:19:49.621242+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2607.06403","citing_title":"From Foundation to Application: Improving VLA Models in Practice","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27144","citing_title":"PAMAE: Phase-Aware-MoE Action Experts Towards Reliable Flow-Matching Vision-Language-Action Policies","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22794","citing_title":"UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10305","citing_title":"SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09337","citing_title":"TORL-VLA: Tactile Guided Online Reinforcement Learning for Contact-Rich Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07993","citing_title":"HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3","json":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3.json","graph_json":"https://pith.science/api/pith-number/N7MKYG4N4GETMHDK6GUXX4PPF3/graph.json","events_json":"https://pith.science/api/pith-number/N7MKYG4N4GETMHDK6GUXX4PPF3/events.json","paper":"https://pith.science/paper/N7MKYG4N"},"agent_actions":{"view_html":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3","download_json":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3.json","view_paper":"https://pith.science/paper/N7MKYG4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.05693&json=true","fetch_graph":"https://pith.science/api/pith-number/N7MKYG4N4GETMHDK6GUXX4PPF3/graph.json","fetch_events":"https://pith.science/api/pith-number/N7MKYG4N4GETMHDK6GUXX4PPF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3/action/storage_attestation","attest_author":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3/action/author_attestation","sign_citation":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3/action/citation_signature","submit_replication":"https://pith.science/pith/N7MKYG4N4GETMHDK6GUXX4PPF3/action/replication_record"}},"created_at":"2026-07-09T01:19:49.621242+00:00","updated_at":"2026-07-09T01:19:49.621242+00:00"}