{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HNKD5BV6A7427ON55LHPHFE64N","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":"6ae3dcd1eea49db2a90dd068561907d37521dfb904cc7d0c831697dc58ea623e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-08T00:28:41Z","title_canon_sha256":"4e9d0a361a626818f0e02e7d5ce43bcedf1c01e3334421bf850cb98011cbba24"},"schema_version":"1.0","source":{"id":"2407.05530","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05530","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05530v2","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05530","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"HNKD5BV6A742","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"HNKD5BV6A7427ON5","created_at":"2026-07-05T11:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"HNKD5BV6","created_at":"2026-07-05T11:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:e72e84d9780b5f2c5dda341a6f80b3b35b1cc1b282d6efc2969ea4f6e3d6073c","target":"graph","created_at":"2026-07-05T11:04:38Z","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/2407.05530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clear, interpretable instructions are invaluable when attempting any complex task. Good instructions help to clarify the task and even anticipate the steps needed to solve it. In this work, we propose a robot learning framework for communicating, planning, and executing a wide range of tasks, dubbed This&That. This&That solves general tasks by leveraging video generative models, which, through training on internet-scale data, contain rich physical and semantic context. In this work, we tackle three fundamental challenges in video-based planning: 1) unambiguous task communication with simple hu","authors_text":"Adam Fishman, Boyang Wang, Chao Feng, Jeong Joon Park, Mark Van der Merwe, Nikhil Sridhar, Nima Fazeli","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-08T00:28:41Z","title":"This&That: Language-Gesture Controlled Video Generation for Robot Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05530","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":"sha256:13b826a2722db7536f4da2adf15e9da29a0cefd826e343f5debe64cd18901a9b","target":"record","created_at":"2026-07-05T11:04:38Z","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":"6ae3dcd1eea49db2a90dd068561907d37521dfb904cc7d0c831697dc58ea623e","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-08T00:28:41Z","title_canon_sha256":"4e9d0a361a626818f0e02e7d5ce43bcedf1c01e3334421bf850cb98011cbba24"},"schema_version":"1.0","source":{"id":"2407.05530","kind":"arxiv","version":2}},"canonical_sha256":"3b543e86be07f9afb9bdeacef3949ee35cbf442b0bc58bb73159d1c01f16dac5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b543e86be07f9afb9bdeacef3949ee35cbf442b0bc58bb73159d1c01f16dac5","first_computed_at":"2026-07-05T11:04:38.268243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:38.268243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9F7b5YPv0xr1Y/gyJ9toEtlrjTa/pWToe1dPfy3hAHXbAlzqIITyAQMGH1d5fx3scYZq24M/psmlXdSews8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:38.268730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05530","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13b826a2722db7536f4da2adf15e9da29a0cefd826e343f5debe64cd18901a9b","sha256:e72e84d9780b5f2c5dda341a6f80b3b35b1cc1b282d6efc2969ea4f6e3d6073c"],"state_sha256":"13265e0844a41b724a4799893ed56b2fdf70f5ec680dde3b2a24e7ea62f17ed9"}