{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WIDBK3J3ZHBZAOJYU7ALNN37SZ","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":"6d20effd2c92ba5be982825c8df0441cc17fc986647455e10cea7e2630305c35","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T17:59:32Z","title_canon_sha256":"0129056e61cc7d42ae795c4cb6cdbc14ceffa5c05dc3ac7383801d23bd257e51"},"schema_version":"1.0","source":{"id":"2505.07817","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07817","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07817v2","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07817","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"WIDBK3J3ZHBZ","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"WIDBK3J3ZHBZAOJY","created_at":"2026-07-05T12:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"WIDBK3J3","created_at":"2026-07-05T12:00:49Z"}],"graph_snapshots":[{"event_id":"sha256:26de697fa737461511cc3df47114e9f34275301978c4cdb5b7dbb95abd9bf221","target":"graph","created_at":"2026-07-05T12:00:49Z","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/2505.07817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present LangToMo, a vision-language-action framework structured as a dual-system architecture that uses pixel motion forecasts as intermediate representations. Our high-level System 2, an image diffusion model, generates text-conditioned pixel motion sequences from a single frame to guide robot control. Pixel motion-a universal, interpretable, and motion-centric representation-can be extracted from videos in a weakly-supervised manner, enabling diffusion model training on any video-caption data. Treating generated pixel motion as learned universal representations, our low level System 1 mod","authors_text":"Cristina Mata, E-Ro Nguyen, Jongwoo Park, Kanchana Ranasinghe, Michael S Ryoo, Xiang Li","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T17:59:32Z","title":"Pixel Motion as Universal Representation for Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07817","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":"sha256:296b6211b0e68c27883b2e411f3609f81fffa389867b602b12984162224df6c8","target":"record","created_at":"2026-07-05T12:00:49Z","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":"6d20effd2c92ba5be982825c8df0441cc17fc986647455e10cea7e2630305c35","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T17:59:32Z","title_canon_sha256":"0129056e61cc7d42ae795c4cb6cdbc14ceffa5c05dc3ac7383801d23bd257e51"},"schema_version":"1.0","source":{"id":"2505.07817","kind":"arxiv","version":2}},"canonical_sha256":"b206156d3bc9c3903938a7c0b6b77f964c2fa4bf51417f193f635644fce2126e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b206156d3bc9c3903938a7c0b6b77f964c2fa4bf51417f193f635644fce2126e","first_computed_at":"2026-07-05T12:00:49.904418Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:49.904418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ho8UclpNROrlDgRmMmn2vJzpkIHN/wG56xd7Tl5cQnVt4uq8DBcp1Evr1JJcWel6XQUU907QIazahLTrYZn1DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:49.904964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07817","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:296b6211b0e68c27883b2e411f3609f81fffa389867b602b12984162224df6c8","sha256:26de697fa737461511cc3df47114e9f34275301978c4cdb5b7dbb95abd9bf221"],"state_sha256":"16fcaea9a4e782bbfb47ba17bf982669c047f6ed0a840197d7d5b7ac72b9fa47"}