{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OE7EKOTBMPZ6YKWJT3P3GWQQNI","short_pith_number":"pith:OE7EKOTB","schema_version":"1.0","canonical_sha256":"713e453a6163f3ec2ac99edfb35a106a1b55e8a75aac9adf4afc2bda5e794448","source":{"kind":"arxiv","id":"2606.03943","version":1},"attestation_state":"computed","paper":{"title":"PointAction: 3D Points as Universal Action Representations for Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Han Jiang, Jiatao Gu, Lingjie Liu, Mutian Tong, Qiao Feng","submitted_at":"2026-06-02T17:30:50Z","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"},"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":"2606.03943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T17:30:50Z","cross_cats_sorted":[],"title_canon_sha256":"601ceb6fcae201bebeeaacba48d15655530d12970e094fb8d30cb3622abd68cf","abstract_canon_sha256":"e38be7f2f49cf8e5778c53e7a7fcc6fa62021e8ade49da34d0880f17ca044e7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:07.567966Z","signature_b64":"Kg/hrsiqtWlOxRBzMHaD7zytd3NNu0TTZwGoOreyCiFQ5ZaHshPgA/s1HUM+lrBH6yB7StnblPoff9aOM9A+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"713e453a6163f3ec2ac99edfb35a106a1b55e8a75aac9adf4afc2bda5e794448","last_reissued_at":"2026-06-03T02:06:07.567547Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:07.567547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PointAction: 3D Points as Universal Action Representations for Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Han Jiang, Jiatao Gu, Lingjie Liu, Mutian Tong, Qiao Feng","submitted_at":"2026-06-02T17:30:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03943","kind":"arxiv","version":1},"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/2606.03943/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":"2606.03943","created_at":"2026-06-03T02:06:07.567613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03943v1","created_at":"2026-06-03T02:06:07.567613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03943","created_at":"2026-06-03T02:06:07.567613+00:00"},{"alias_kind":"pith_short_12","alias_value":"OE7EKOTBMPZ6","created_at":"2026-06-03T02:06:07.567613+00:00"},{"alias_kind":"pith_short_16","alias_value":"OE7EKOTBMPZ6YKWJ","created_at":"2026-06-03T02:06:07.567613+00:00"},{"alias_kind":"pith_short_8","alias_value":"OE7EKOTB","created_at":"2026-06-03T02:06:07.567613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI","json":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI.json","graph_json":"https://pith.science/api/pith-number/OE7EKOTBMPZ6YKWJT3P3GWQQNI/graph.json","events_json":"https://pith.science/api/pith-number/OE7EKOTBMPZ6YKWJT3P3GWQQNI/events.json","paper":"https://pith.science/paper/OE7EKOTB"},"agent_actions":{"view_html":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI","download_json":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI.json","view_paper":"https://pith.science/paper/OE7EKOTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03943&json=true","fetch_graph":"https://pith.science/api/pith-number/OE7EKOTBMPZ6YKWJT3P3GWQQNI/graph.json","fetch_events":"https://pith.science/api/pith-number/OE7EKOTBMPZ6YKWJT3P3GWQQNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI/action/storage_attestation","attest_author":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI/action/author_attestation","sign_citation":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI/action/citation_signature","submit_replication":"https://pith.science/pith/OE7EKOTBMPZ6YKWJT3P3GWQQNI/action/replication_record"}},"created_at":"2026-06-03T02:06:07.567613+00:00","updated_at":"2026-06-03T02:06:07.567613+00:00"}