{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4FABLZ2EHQTWUHSJT6OWVVEHKK","short_pith_number":"pith:4FABLZ2E","canonical_record":{"source":{"id":"2406.16862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-24T17:59:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b345b7bc789d0771251aefb7731d2dcdfd7350079959a4cdaedb6338b44e94df","abstract_canon_sha256":"ca16d16a445fd2ab8f1352dd456f3b1b9d6bc71dd84069aabe63afa8bfcfce4d"},"schema_version":"1.0"},"canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","source":{"kind":"arxiv","id":"2406.16862","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16862","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16862v1","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16862","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"4FABLZ2EHQTW","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"4FABLZ2EHQTWUHSJ","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"4FABLZ2E","created_at":"2026-07-05T08:36:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4FABLZ2EHQTWUHSJT6OWVVEHKK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16862","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-24T17:59:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b345b7bc789d0771251aefb7731d2dcdfd7350079959a4cdaedb6338b44e94df","abstract_canon_sha256":"ca16d16a445fd2ab8f1352dd456f3b1b9d6bc71dd84069aabe63afa8bfcfce4d"},"schema_version":"1.0"},"canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:04.681441Z","signature_b64":"1me0iFL8fuwLxDWkOS7Emyfh5ULBNSTcLAw9XPgQTM+uyKijdfkbjZQiigtYSbPhlW2F0ffL/h7WeUIVmXb6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","last_reissued_at":"2026-07-05T08:36:04.680964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:04.680964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16862","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sp6foQvLm1T2faVXogMUpLqLsiu8BeZAHjJABtC0oGrKFm1698fJWDS8NoO04AOo95FS3YewIHvBbtXbm5kBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:56:45.632123Z"},"content_sha256":"28f7414f0b11a0f7fcb6b6fd64384f30801f33b856f92dc6f4b9459329b3c0ff","schema_version":"1.0","event_id":"sha256:28f7414f0b11a0f7fcb6b6fd64384f30801f33b856f92dc6f4b9459329b3c0ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4FABLZ2EHQTWUHSJT6OWVVEHKK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Achal Dave, Carl Vondrick, Ege Ozguroglu, Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Shuran Song, Sruthi Sudhakar","submitted_at":"2024-06-24T17:59:45Z","abstract_excerpt":"A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of internet videos. In this paper, we propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. At test time, we generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot. Our key insig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16862","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/2406.16862/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8IGIHccJS20oYVXsBu2lzvjjoQ9+zgzpIVcb+uWCcZLDd/b23lzlu2hJ9LeL8l5o3chFJXUic7YB+OFyzMZSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:56:45.632682Z"},"content_sha256":"4676296c6f1fdfb4555e66fda0a750b3672ee15952ed1430bc36d6dc51b3b149","schema_version":"1.0","event_id":"sha256:4676296c6f1fdfb4555e66fda0a750b3672ee15952ed1430bc36d6dc51b3b149"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/bundle.json","state_url":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T11:56:45Z","links":{"resolver":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK","bundle":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/bundle.json","state":"https://pith.science/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FABLZ2EHQTWUHSJT6OWVVEHKK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4FABLZ2EHQTWUHSJT6OWVVEHKK","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":"ca16d16a445fd2ab8f1352dd456f3b1b9d6bc71dd84069aabe63afa8bfcfce4d","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-24T17:59:45Z","title_canon_sha256":"b345b7bc789d0771251aefb7731d2dcdfd7350079959a4cdaedb6338b44e94df"},"schema_version":"1.0","source":{"id":"2406.16862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16862","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16862v1","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16862","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"4FABLZ2EHQTW","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_16","alias_value":"4FABLZ2EHQTWUHSJ","created_at":"2026-07-05T08:36:04Z"},{"alias_kind":"pith_short_8","alias_value":"4FABLZ2E","created_at":"2026-07-05T08:36:04Z"}],"graph_snapshots":[{"event_id":"sha256:4676296c6f1fdfb4555e66fda0a750b3672ee15952ed1430bc36d6dc51b3b149","target":"graph","created_at":"2026-07-05T08:36:04Z","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/2406.16862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale datasets of internet videos. In this paper, we propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task. At test time, we generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot. Our key insig","authors_text":"Achal Dave, Carl Vondrick, Ege Ozguroglu, Junbang Liang, Pavel Tokmakov, Ruoshi Liu, Shuran Song, Sruthi Sudhakar","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-24T17:59:45Z","title":"Dreamitate: Real-World Visuomotor Policy Learning via Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16862","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":"sha256:28f7414f0b11a0f7fcb6b6fd64384f30801f33b856f92dc6f4b9459329b3c0ff","target":"record","created_at":"2026-07-05T08:36:04Z","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":"ca16d16a445fd2ab8f1352dd456f3b1b9d6bc71dd84069aabe63afa8bfcfce4d","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-24T17:59:45Z","title_canon_sha256":"b345b7bc789d0771251aefb7731d2dcdfd7350079959a4cdaedb6338b44e94df"},"schema_version":"1.0","source":{"id":"2406.16862","kind":"arxiv","version":1}},"canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e14015e7443c276a1e499f9d6ad48752ba21836d9d2b99f8d374279cb92fa5bf","first_computed_at":"2026-07-05T08:36:04.680964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:04.680964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1me0iFL8fuwLxDWkOS7Emyfh5ULBNSTcLAw9XPgQTM+uyKijdfkbjZQiigtYSbPhlW2F0ffL/h7WeUIVmXb6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:04.681441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28f7414f0b11a0f7fcb6b6fd64384f30801f33b856f92dc6f4b9459329b3c0ff","sha256:4676296c6f1fdfb4555e66fda0a750b3672ee15952ed1430bc36d6dc51b3b149"],"state_sha256":"4cdc7fceaf9409ca7ec796e24d0fe8f437b5d423dd05be3092d538dd69e5b6dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Wmio/q7od9qklB3cGwtQCEweP4M0jrSAaLRYDfqoLlrjFNowYP05ZMAiZcbWFVOcamOg8xbwjjbtMT8c/aKCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:56:45.642251Z","bundle_sha256":"19dd2a7fa303ae1a46b5bae5335a6e73a430225b1a4b8e593fa4ac2883db4fbf"}}