{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XAMNDPA7WZDZYELPKX2PSLF4XK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3b29400f090535b09e12c240fd3b94e48fd64f792bf397c87a2e4e0d788eb324","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-28T09:39:37Z","title_canon_sha256":"798d0cc456f59471044f64bbff1b6da46a22c6cb8e236f30fb1c40c863ffc01b"},"schema_version":"1.0","source":{"id":"2506.22827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22827","created_at":"2026-07-05T11:34:52Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22827v3","created_at":"2026-07-05T11:34:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22827","created_at":"2026-07-05T11:34:52Z"},{"alias_kind":"pith_short_12","alias_value":"XAMNDPA7WZDZ","created_at":"2026-07-05T11:34:52Z"},{"alias_kind":"pith_short_16","alias_value":"XAMNDPA7WZDZYELP","created_at":"2026-07-05T11:34:52Z"},{"alias_kind":"pith_short_8","alias_value":"XAMNDPA7","created_at":"2026-07-05T11:34:52Z"}],"graph_snapshots":[{"event_id":"sha256:750c7c3ff5c66cd274b944b31d7700287768f973eaed012568c42e7b389749af","target":"graph","created_at":"2026-07-05T11:34:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.22827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andr\\'e Schakkal, Ben Zandonati, Navid Azizan, Zhutian Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-28T09:39:37Z","title":"Hierarchical Vision-Language Planning for Multi-Step Humanoid Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22827","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:855e3045811ea64780f2e720a2379f0bb9e609e2dd2ed32a7124aec1dee027fa","target":"record","created_at":"2026-07-05T11:34:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3b29400f090535b09e12c240fd3b94e48fd64f792bf397c87a2e4e0d788eb324","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-28T09:39:37Z","title_canon_sha256":"798d0cc456f59471044f64bbff1b6da46a22c6cb8e236f30fb1c40c863ffc01b"},"schema_version":"1.0","source":{"id":"2506.22827","kind":"arxiv","version":3}},"canonical_sha256":"b818d1bc1fb6479c116f55f4f92cbcbab20dd6aaa9844686c1ad18a4c988d37f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b818d1bc1fb6479c116f55f4f92cbcbab20dd6aaa9844686c1ad18a4c988d37f","first_computed_at":"2026-07-05T11:34:52.574944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:52.574944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0OL6W+nJeD7gBLm1K6ojd1m9B/tz/iUrh8LWzo2+6e0mbDuolyUoCOj84JUha61lYDtm28OA4D28ePzRL159Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:52.575510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:855e3045811ea64780f2e720a2379f0bb9e609e2dd2ed32a7124aec1dee027fa","sha256:750c7c3ff5c66cd274b944b31d7700287768f973eaed012568c42e7b389749af"],"state_sha256":"499d8c310b61903be2d46e6026ceda0c6f3b9c4a3ab13b08355468219510f491"}