{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:25ZPKNVJDBJ3GIPY4GWTVOR3CS","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":"dbcee669ad04195f93f51972450ed1e158d062f807d46dea019b1a3a5a002b80","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-01-28T07:50:30Z","title_canon_sha256":"b45787df9f5620b98fffb31d715ab948331825086c2d395c73d6bc2de0444899"},"schema_version":"1.0","source":{"id":"2602.02533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02533","created_at":"2026-07-23T01:23:33Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02533v1","created_at":"2026-07-23T01:23:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02533","created_at":"2026-07-23T01:23:33Z"},{"alias_kind":"pith_short_12","alias_value":"25ZPKNVJDBJ3","created_at":"2026-07-23T01:23:33Z"},{"alias_kind":"pith_short_16","alias_value":"25ZPKNVJDBJ3GIPY","created_at":"2026-07-23T01:23:33Z"},{"alias_kind":"pith_short_8","alias_value":"25ZPKNVJ","created_at":"2026-07-23T01:23:33Z"}],"graph_snapshots":[{"event_id":"sha256:83a97bf5cb70bb2661e48329fdb4f62e189d2198328b4497cf3f69e67903450d","target":"graph","created_at":"2026-07-23T01:23:33Z","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/2602.02533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Language Action (VLA) models have recently shown great potential in bridging multimodal perception with robotic control. However, existing methods often rely on direct fine-tuning of pre-trained Vision-Language Models (VLMs), feeding semantic and visual features directly into a policy network without fully addressing the unique semantic alignment challenges in the VLA domain. In this paper, we propose HMVLA, a novel VLA framework that exploits the inherent hierarchical structures in vision and language for comprehensive semantic alignment. Unlike traditional methods that perform alignme","authors_text":"Kun Wang, Mingcheng Qu, Tonghua Su, Xiao Feng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-01-28T07:50:30Z","title":"HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02533","kind":"arxiv","version":1},"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":"sha256:0e278beedee4f12f953d4dc875f7cb6fc73d8752c685c42bb095321f0ecac7f5","target":"record","created_at":"2026-07-23T01:23:33Z","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":"dbcee669ad04195f93f51972450ed1e158d062f807d46dea019b1a3a5a002b80","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-01-28T07:50:30Z","title_canon_sha256":"b45787df9f5620b98fffb31d715ab948331825086c2d395c73d6bc2de0444899"},"schema_version":"1.0","source":{"id":"2602.02533","kind":"arxiv","version":1}},"canonical_sha256":"d772f536a91853b321f8e1ad3aba3b148dcf614159ed2763150e779f4ae2137e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d772f536a91853b321f8e1ad3aba3b148dcf614159ed2763150e779f4ae2137e","first_computed_at":"2026-07-23T01:23:33.017580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:23:33.017580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+Efwopzn2z2/6HJIuoVVPdHFS0JSuoDY9Wb0oEM9/bc41rrYBksb4345o96wcMxrHGDlbgv+QXsmDJIJlmMDA==","signature_status":"signed_v1","signed_at":"2026-07-23T01:23:33.018540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.02533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e278beedee4f12f953d4dc875f7cb6fc73d8752c685c42bb095321f0ecac7f5","sha256:83a97bf5cb70bb2661e48329fdb4f62e189d2198328b4497cf3f69e67903450d"],"state_sha256":"c19cf6afe0e088c6c5c1f19a16b4c538d5aa9b773532fd268b40d13d062e03bc"}