{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SSKMQM3SNZWW2M3WZ7UTPI25VM","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":"b1709173bb889a1175a77e109d03c6a388d5e3927319af8f1730366cd0ae551a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-20T18:17:11Z","title_canon_sha256":"69cec354a5fc41f114a55a279144403716e3e409e3ffa76f1d760a30e29c2337"},"schema_version":"1.0","source":{"id":"2502.14795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14795","created_at":"2026-07-05T10:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14795v2","created_at":"2026-07-05T10:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14795","created_at":"2026-07-05T10:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"SSKMQM3SNZWW","created_at":"2026-07-05T10:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"SSKMQM3SNZWW2M3W","created_at":"2026-07-05T10:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"SSKMQM3S","created_at":"2026-07-05T10:17:55Z"}],"graph_snapshots":[{"event_id":"sha256:3c14710da9868dd041c8cb2e595892775de50b051e98274b54a4b74a9e73fcd8","target":"graph","created_at":"2026-07-05T10:17:55Z","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/2502.14795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the limitations of current humanoid robot control frameworks, which primarily rely on reactive mechanisms and lack autonomous interaction capabilities due to data scarcity. We propose Humanoid-VLA, a novel framework that integrates language understanding, egocentric scene perception, and motion control, enabling universal humanoid control. Humanoid-VLA begins with language-motion pre-alignment using non-egocentric human motion datasets paired with textual descriptions, allowing the model to learn universal motion patterns and action semantics. We then incorporate egocentri","authors_text":"Binghong Zou, Donglin Wang, Hongchao Lu, Huaicheng Zhou, Jiacheng Liu, Jianfei Ma, Jinxin Liu, Panzhong Mo, Pengxiang Ding, Siteng Huang, Ting Wang, Wenshuo Feng, Xinxin Luo, Xinyang Tong, Yiguo Fan, Yuefan Wang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-20T18:17:11Z","title":"Humanoid-VLA: Towards Universal Humanoid Control with Visual Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14795","kind":"arxiv","version":2},"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":"sha256:3cc49de8ea82920215ccdee3877ea29266efbe8418d2c2830ed37f9f57f15efa","target":"record","created_at":"2026-07-05T10:17:55Z","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":"b1709173bb889a1175a77e109d03c6a388d5e3927319af8f1730366cd0ae551a","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-20T18:17:11Z","title_canon_sha256":"69cec354a5fc41f114a55a279144403716e3e409e3ffa76f1d760a30e29c2337"},"schema_version":"1.0","source":{"id":"2502.14795","kind":"arxiv","version":2}},"canonical_sha256":"9494c833726e6d6d3376cfe937a35dab0dc4de897fddd8717deda034be3d5f2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9494c833726e6d6d3376cfe937a35dab0dc4de897fddd8717deda034be3d5f2b","first_computed_at":"2026-07-05T10:17:55.275275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:55.275275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uj/y0c8yphYDiz/idedyBDoDXP4GrAyVS9AGoASrrjZhNtco3o6B0A8nhYq4Ir0KA2BGgLgsCmAjum2/k1DCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:55.275901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cc49de8ea82920215ccdee3877ea29266efbe8418d2c2830ed37f9f57f15efa","sha256:3c14710da9868dd041c8cb2e595892775de50b051e98274b54a4b74a9e73fcd8"],"state_sha256":"8f532dfbbf3d3ee43302d7c1e0730c31ab6621ac0e3e757d4353c4a0b9e9efa2"}