{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XAMNDPA7WZDZYELPKX2PSLF4XK","short_pith_number":"pith:XAMNDPA7","schema_version":"1.0","canonical_sha256":"b818d1bc1fb6479c116f55f4f92cbcbab20dd6aaa9844686c1ad18a4c988d37f","source":{"kind":"arxiv","id":"2506.22827","version":3},"attestation_state":"computed","paper":{"title":"Hierarchical Vision-Language Planning for Multi-Step Humanoid Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andr\\'e Schakkal, Ben Zandonati, Navid Azizan, Zhutian Yang","submitted_at":"2025-06-28T09:39:37Z","abstract_excerpt":"Enabling humanoid robots to reliably execute complex multi-step manipulation tasks is crucial for their effective deployment in industrial and household environments. This paper presents a hierarchical planning and control framework designed to achieve reliable multi-step humanoid manipulation. The proposed system comprises three layers: (1) a low-level RL-based controller responsible for tracking whole-body motion targets; (2) a mid-level set of skill policies trained via imitation learning that produce motion targets for different steps of a task; and (3) a high-level vision-language plannin"},"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":"2506.22827","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-28T09:39:37Z","cross_cats_sorted":[],"title_canon_sha256":"798d0cc456f59471044f64bbff1b6da46a22c6cb8e236f30fb1c40c863ffc01b","abstract_canon_sha256":"3b29400f090535b09e12c240fd3b94e48fd64f792bf397c87a2e4e0d788eb324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:52.575510Z","signature_b64":"0OL6W+nJeD7gBLm1K6ojd1m9B/tz/iUrh8LWzo2+6e0mbDuolyUoCOj84JUha61lYDtm28OA4D28ePzRL159Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b818d1bc1fb6479c116f55f4f92cbcbab20dd6aaa9844686c1ad18a4c988d37f","last_reissued_at":"2026-07-05T11:34:52.574944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:52.574944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Vision-Language Planning for Multi-Step Humanoid Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andr\\'e Schakkal, Ben Zandonati, Navid Azizan, Zhutian Yang","submitted_at":"2025-06-28T09:39:37Z","abstract_excerpt":"Enabling humanoid robots to reliably execute complex multi-step manipulation tasks is crucial for their effective deployment in industrial and household environments. This paper presents a hierarchical planning and control framework designed to achieve reliable multi-step humanoid manipulation. The proposed system comprises three layers: (1) a low-level RL-based controller responsible for tracking whole-body motion targets; (2) a mid-level set of skill policies trained via imitation learning that produce motion targets for different steps of a task; and (3) a high-level vision-language plannin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22827","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/2506.22827/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":"2506.22827","created_at":"2026-07-05T11:34:52.575010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22827v3","created_at":"2026-07-05T11:34:52.575010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22827","created_at":"2026-07-05T11:34:52.575010+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAMNDPA7WZDZ","created_at":"2026-07-05T11:34:52.575010+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAMNDPA7WZDZYELP","created_at":"2026-07-05T11:34:52.575010+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAMNDPA7","created_at":"2026-07-05T11:34:52.575010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26201","citing_title":"OmniContact: Chaining Meta-Skills via Contact Flow for Generalizable Humanoid Loco-Manipulation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07723","citing_title":"VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK","json":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK.json","graph_json":"https://pith.science/api/pith-number/XAMNDPA7WZDZYELPKX2PSLF4XK/graph.json","events_json":"https://pith.science/api/pith-number/XAMNDPA7WZDZYELPKX2PSLF4XK/events.json","paper":"https://pith.science/paper/XAMNDPA7"},"agent_actions":{"view_html":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK","download_json":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK.json","view_paper":"https://pith.science/paper/XAMNDPA7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22827&json=true","fetch_graph":"https://pith.science/api/pith-number/XAMNDPA7WZDZYELPKX2PSLF4XK/graph.json","fetch_events":"https://pith.science/api/pith-number/XAMNDPA7WZDZYELPKX2PSLF4XK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK/action/storage_attestation","attest_author":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK/action/author_attestation","sign_citation":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK/action/citation_signature","submit_replication":"https://pith.science/pith/XAMNDPA7WZDZYELPKX2PSLF4XK/action/replication_record"}},"created_at":"2026-07-05T11:34:52.575010+00:00","updated_at":"2026-07-05T11:34:52.575010+00:00"}