{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J2HWQRS5VUOLVOKDB73BQ44YRZ","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":"b3d0088ae817d6efc5a8ca5b11b0dd504f9b8e97e03d35fbafefd51d8da4654a","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T17:41:10Z","title_canon_sha256":"25e9aeb70855171c44436afc4b7c67e66372f9a743206120aa00c4074af6c1fd"},"schema_version":"1.0","source":{"id":"2407.07875","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07875","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07875v2","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07875","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"J2HWQRS5VUOL","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"J2HWQRS5VUOLVOKD","created_at":"2026-07-05T09:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"J2HWQRS5","created_at":"2026-07-05T09:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:79e30a02048581feb42cf16fbd0362cea6bfbf87ff5ac4777026fb76d0a742cf","target":"graph","created_at":"2026-07-05T09:17:45Z","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/2407.07875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-generation diffusion models have been fine-tuned to unlock new capabilities such as image-editing and novel view synthesis. Can we similarly unlock image-generation models for visuomotor control? We present GENIMA, a behavior-cloning agent that fine-tunes Stable Diffusion to 'draw joint-actions' as targets on RGB images. These images are fed into a controller that maps the visual targets into a sequence of joint-positions. We study GENIMA on 25 RLBench and 9 real-world manipulation tasks. We find that, by lifting actions into image-space, internet pre-trained diffusion models can generat","authors_text":"Mohit Shridhar, Stephen James, Yat Long Lo","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T17:41:10Z","title":"Generative Image as Action Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07875","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":"sha256:0da13c65afb7420d6a90db40681ea84a34d78750f41e45a964ef023e9ac5ec90","target":"record","created_at":"2026-07-05T09:17:45Z","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":"b3d0088ae817d6efc5a8ca5b11b0dd504f9b8e97e03d35fbafefd51d8da4654a","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-10T17:41:10Z","title_canon_sha256":"25e9aeb70855171c44436afc4b7c67e66372f9a743206120aa00c4074af6c1fd"},"schema_version":"1.0","source":{"id":"2407.07875","kind":"arxiv","version":2}},"canonical_sha256":"4e8f68465dad1cbab9430ff61873988e5ee0df1af61c0a95b450341870c86376","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e8f68465dad1cbab9430ff61873988e5ee0df1af61c0a95b450341870c86376","first_computed_at":"2026-07-05T09:17:45.738174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:45.738174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WBQYhgQVMaZFAnKSFZj8+iXxgty5Dcx4t9duH93WY/Q4K+vYShfBFht70lCjmxQKKLuZB2X5/cxQA2s9sItYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:45.738644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07875","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0da13c65afb7420d6a90db40681ea84a34d78750f41e45a964ef023e9ac5ec90","sha256:79e30a02048581feb42cf16fbd0362cea6bfbf87ff5ac4777026fb76d0a742cf"],"state_sha256":"e9ef974a75ac8d0e23faf610be1a18d9eabf5c5a2d38de324a6aeb345eed254e"}