{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OE7EKOTBMPZ6YKWJT3P3GWQQNI","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":"e38be7f2f49cf8e5778c53e7a7fcc6fa62021e8ade49da34d0880f17ca044e7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:30:50Z","title_canon_sha256":"601ceb6fcae201bebeeaacba48d15655530d12970e094fb8d30cb3622abd68cf"},"schema_version":"1.0","source":{"id":"2606.03943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.03943","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.03943v1","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03943","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"OE7EKOTBMPZ6","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"OE7EKOTBMPZ6YKWJ","created_at":"2026-06-03T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"OE7EKOTB","created_at":"2026-06-03T02:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:c1f62df7ea56f9eab27cd2cea6894232cc9661a03e91c6d3e0072ad80914612b","target":"graph","created_at":"2026-06-03T02:06:07Z","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/2606.03943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation. However, RGB-only video rollouts are not directly actionable: they leave metric 3D motion, contact geometry, and fine-grained spatial constraints under-specified, making action grounding ambiguous. Meanwhile, scaling action supervision across diverse tasks and embodiments remains costly. We present PointAction, a framework that bridges video predictions to robot actions through explicit point-based 4D modeling. PointAct","authors_text":"Han Jiang, Jiatao Gu, Lingjie Liu, Mutian Tong, Qiao Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:30:50Z","title":"PointAction: 3D Points as Universal Action Representations for Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03943","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:a7e8ffcacf7843eae1a76cfd34eee431a954676076ab223f8ec9dc3ff459fc4c","target":"record","created_at":"2026-06-03T02:06:07Z","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":"e38be7f2f49cf8e5778c53e7a7fcc6fa62021e8ade49da34d0880f17ca044e7b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:30:50Z","title_canon_sha256":"601ceb6fcae201bebeeaacba48d15655530d12970e094fb8d30cb3622abd68cf"},"schema_version":"1.0","source":{"id":"2606.03943","kind":"arxiv","version":1}},"canonical_sha256":"713e453a6163f3ec2ac99edfb35a106a1b55e8a75aac9adf4afc2bda5e794448","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"713e453a6163f3ec2ac99edfb35a106a1b55e8a75aac9adf4afc2bda5e794448","first_computed_at":"2026-06-03T02:06:07.567547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T02:06:07.567547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kg/hrsiqtWlOxRBzMHaD7zytd3NNu0TTZwGoOreyCiFQ5ZaHshPgA/s1HUM+lrBH6yB7StnblPoff9aOM9A+Dg==","signature_status":"signed_v1","signed_at":"2026-06-03T02:06:07.567966Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.03943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7e8ffcacf7843eae1a76cfd34eee431a954676076ab223f8ec9dc3ff459fc4c","sha256:c1f62df7ea56f9eab27cd2cea6894232cc9661a03e91c6d3e0072ad80914612b"],"state_sha256":"e5b809c75a228ba90b6a65d31fb2baedf0a83617e32e0c4dfc1dc2b8dfd6916d"}