{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:COHSFV4VOKSAH7VNWGLZ5QVA6V","short_pith_number":"pith:COHSFV4V","schema_version":"1.0","canonical_sha256":"138f22d79572a403feadb1979ec2a0f576fadc1f0c4d0fcfbd357fe511b32e1b","source":{"kind":"arxiv","id":"2606.24448","version":1},"attestation_state":"computed","paper":{"title":"Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chen Gao, Danze Chen, Mike Zheng Shou, Qiming Huang, Yanzhe Chen, Zhijun Cao","submitted_at":"2026-06-23T11:35:13Z","abstract_excerpt":"Vision-Language-Action (VLA) models require large-scale video-action pairs, yet real teleoperation remains scarce. While generated robot videos offer a scalable alternative, existing methods treat them as real robot data by recovering pseudo-actions from synthesized pixels. We argue that deriving low-level control from generated visuals is a mismatched abstraction. A video captures only \\emph{geometry}: the spatial trajectory representing the \\emph{where} of a task. A real demonstration captures \\emph{control}: the exact motor commands representing the \\emph{how}. Human-to-robot video generati"},"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":"2606.24448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-23T11:35:13Z","cross_cats_sorted":[],"title_canon_sha256":"068ba6cf3ae78ae782536f925efff18620a33567bd9bf91b5305fd7e29c3c3cf","abstract_canon_sha256":"a69996abd4e9a03f9441e5aed746d1bddacffb564c27c003472d1efcafa29789"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:30.688348Z","signature_b64":"DUwT2yTov55BKeByXmJspLUvkNpo9QgD6pcKJy1epshbsykBsqMPyWre2DhDgVo0UQDJ1xobMmeML/TWmC8PAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"138f22d79572a403feadb1979ec2a0f576fadc1f0c4d0fcfbd357fe511b32e1b","last_reissued_at":"2026-06-24T01:15:30.687976Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:30.687976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chen Gao, Danze Chen, Mike Zheng Shou, Qiming Huang, Yanzhe Chen, Zhijun Cao","submitted_at":"2026-06-23T11:35:13Z","abstract_excerpt":"Vision-Language-Action (VLA) models require large-scale video-action pairs, yet real teleoperation remains scarce. While generated robot videos offer a scalable alternative, existing methods treat them as real robot data by recovering pseudo-actions from synthesized pixels. We argue that deriving low-level control from generated visuals is a mismatched abstraction. A video captures only \\emph{geometry}: the spatial trajectory representing the \\emph{where} of a task. A real demonstration captures \\emph{control}: the exact motor commands representing the \\emph{how}. Human-to-robot video generati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24448","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/2606.24448/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":"2606.24448","created_at":"2026-06-24T01:15:30.688040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24448v1","created_at":"2026-06-24T01:15:30.688040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24448","created_at":"2026-06-24T01:15:30.688040+00:00"},{"alias_kind":"pith_short_12","alias_value":"COHSFV4VOKSA","created_at":"2026-06-24T01:15:30.688040+00:00"},{"alias_kind":"pith_short_16","alias_value":"COHSFV4VOKSAH7VN","created_at":"2026-06-24T01:15:30.688040+00:00"},{"alias_kind":"pith_short_8","alias_value":"COHSFV4V","created_at":"2026-06-24T01:15:30.688040+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/COHSFV4VOKSAH7VNWGLZ5QVA6V","json":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V.json","graph_json":"https://pith.science/api/pith-number/COHSFV4VOKSAH7VNWGLZ5QVA6V/graph.json","events_json":"https://pith.science/api/pith-number/COHSFV4VOKSAH7VNWGLZ5QVA6V/events.json","paper":"https://pith.science/paper/COHSFV4V"},"agent_actions":{"view_html":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V","download_json":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V.json","view_paper":"https://pith.science/paper/COHSFV4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24448&json=true","fetch_graph":"https://pith.science/api/pith-number/COHSFV4VOKSAH7VNWGLZ5QVA6V/graph.json","fetch_events":"https://pith.science/api/pith-number/COHSFV4VOKSAH7VNWGLZ5QVA6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V/action/storage_attestation","attest_author":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V/action/author_attestation","sign_citation":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V/action/citation_signature","submit_replication":"https://pith.science/pith/COHSFV4VOKSAH7VNWGLZ5QVA6V/action/replication_record"}},"created_at":"2026-06-24T01:15:30.688040+00:00","updated_at":"2026-06-24T01:15:30.688040+00:00"}