{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNKD5BV6A7427ON55LHPHFE64N","short_pith_number":"pith:HNKD5BV6","schema_version":"1.0","canonical_sha256":"3b543e86be07f9afb9bdeacef3949ee35cbf442b0bc58bb73159d1c01f16dac5","source":{"kind":"arxiv","id":"2407.05530","version":2},"attestation_state":"computed","paper":{"title":"This&That: Language-Gesture Controlled Video Generation for Robot Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Adam Fishman, Boyang Wang, Chao Feng, Jeong Joon Park, Mark Van der Merwe, Nikhil Sridhar, Nima Fazeli","submitted_at":"2024-07-08T00:28:41Z","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"},"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":"2407.05530","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-08T00:28:41Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"4e9d0a361a626818f0e02e7d5ce43bcedf1c01e3334421bf850cb98011cbba24","abstract_canon_sha256":"6ae3dcd1eea49db2a90dd068561907d37521dfb904cc7d0c831697dc58ea623e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:38.268730Z","signature_b64":"v9F7b5YPv0xr1Y/gyJ9toEtlrjTa/pWToe1dPfy3hAHXbAlzqIITyAQMGH1d5fx3scYZq24M/psmlXdSews8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b543e86be07f9afb9bdeacef3949ee35cbf442b0bc58bb73159d1c01f16dac5","last_reissued_at":"2026-07-05T11:04:38.268243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:38.268243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"This&That: Language-Gesture Controlled Video Generation for Robot Planning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Adam Fishman, Boyang Wang, Chao Feng, Jeong Joon Park, Mark Van der Merwe, Nikhil Sridhar, Nima Fazeli","submitted_at":"2024-07-08T00:28:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05530","kind":"arxiv","version":2},"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/2407.05530/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":"2407.05530","created_at":"2026-07-05T11:04:38.268302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05530v2","created_at":"2026-07-05T11:04:38.268302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05530","created_at":"2026-07-05T11:04:38.268302+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNKD5BV6A742","created_at":"2026-07-05T11:04:38.268302+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNKD5BV6A7427ON5","created_at":"2026-07-05T11:04:38.268302+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNKD5BV6","created_at":"2026-07-05T11:04:38.268302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25285","citing_title":"PR-Aware Automated Unit Test Generation: Challenges and Opportunities","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N","json":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N.json","graph_json":"https://pith.science/api/pith-number/HNKD5BV6A7427ON55LHPHFE64N/graph.json","events_json":"https://pith.science/api/pith-number/HNKD5BV6A7427ON55LHPHFE64N/events.json","paper":"https://pith.science/paper/HNKD5BV6"},"agent_actions":{"view_html":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N","download_json":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N.json","view_paper":"https://pith.science/paper/HNKD5BV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05530&json=true","fetch_graph":"https://pith.science/api/pith-number/HNKD5BV6A7427ON55LHPHFE64N/graph.json","fetch_events":"https://pith.science/api/pith-number/HNKD5BV6A7427ON55LHPHFE64N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N/action/storage_attestation","attest_author":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N/action/author_attestation","sign_citation":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N/action/citation_signature","submit_replication":"https://pith.science/pith/HNKD5BV6A7427ON55LHPHFE64N/action/replication_record"}},"created_at":"2026-07-05T11:04:38.268302+00:00","updated_at":"2026-07-05T11:04:38.268302+00:00"}