{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K7RIGKHYIZMHSSGXFXBNVV7ULP","short_pith_number":"pith:K7RIGKHY","schema_version":"1.0","canonical_sha256":"57e28328f846587948d72dc2dad7f45be371a488b3141235da47c5a32da43fd9","source":{"kind":"arxiv","id":"2304.14391","version":4},"attestation_state":"computed","paper":{"title":"Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ayush Jain, Christopher Atkeson, Katerina Fragkiadaki, Nikolaos Gkanatsios, Yunchu Zhang, Zhou Xian","submitted_at":"2023-04-27T17:55:13Z","abstract_excerpt":"Language is compositional; an instruction can express multiple relation constraints to hold among objects in a scene that a robot is tasked to rearrange. Our focus in this work is an instructable scene-rearranging framework that generalizes to longer instructions and to spatial concept compositions never seen at training time. We propose to represent language-instructed spatial concepts with energy functions over relative object arrangements. A language parser maps instructions to corresponding energy functions and an open-vocabulary visual-language model grounds their arguments to relevant ob"},"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":"2304.14391","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-27T17:55:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"a99e69639e7a5eb5beb568d761080162bddce51082c05ba2a67f828498ea601f","abstract_canon_sha256":"ad23d5839ccd2927c1733c3e2fabc981b7be16928de76a09cd878e9e4d65ce80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:20.944077Z","signature_b64":"eqBLsvr/0XD7rtMafk5BjS2lJy8C5mL6SFYvDZ2j0syuLdZ9gMyWTcc+sCqqkditG4GNbaVEfjZMMrM5y8YBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57e28328f846587948d72dc2dad7f45be371a488b3141235da47c5a32da43fd9","last_reissued_at":"2026-07-05T07:36:20.943659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:20.943659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ayush Jain, Christopher Atkeson, Katerina Fragkiadaki, Nikolaos Gkanatsios, Yunchu Zhang, Zhou Xian","submitted_at":"2023-04-27T17:55:13Z","abstract_excerpt":"Language is compositional; an instruction can express multiple relation constraints to hold among objects in a scene that a robot is tasked to rearrange. Our focus in this work is an instructable scene-rearranging framework that generalizes to longer instructions and to spatial concept compositions never seen at training time. We propose to represent language-instructed spatial concepts with energy functions over relative object arrangements. A language parser maps instructions to corresponding energy functions and an open-vocabulary visual-language model grounds their arguments to relevant ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14391","kind":"arxiv","version":4},"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/2304.14391/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":"2304.14391","created_at":"2026-07-05T07:36:20.943714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14391v4","created_at":"2026-07-05T07:36:20.943714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14391","created_at":"2026-07-05T07:36:20.943714+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7RIGKHYIZMH","created_at":"2026-07-05T07:36:20.943714+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7RIGKHYIZMHSSGX","created_at":"2026-07-05T07:36:20.943714+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7RIGKHY","created_at":"2026-07-05T07:36:20.943714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP","json":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP.json","graph_json":"https://pith.science/api/pith-number/K7RIGKHYIZMHSSGXFXBNVV7ULP/graph.json","events_json":"https://pith.science/api/pith-number/K7RIGKHYIZMHSSGXFXBNVV7ULP/events.json","paper":"https://pith.science/paper/K7RIGKHY"},"agent_actions":{"view_html":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP","download_json":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP.json","view_paper":"https://pith.science/paper/K7RIGKHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14391&json=true","fetch_graph":"https://pith.science/api/pith-number/K7RIGKHYIZMHSSGXFXBNVV7ULP/graph.json","fetch_events":"https://pith.science/api/pith-number/K7RIGKHYIZMHSSGXFXBNVV7ULP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP/action/storage_attestation","attest_author":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP/action/author_attestation","sign_citation":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP/action/citation_signature","submit_replication":"https://pith.science/pith/K7RIGKHYIZMHSSGXFXBNVV7ULP/action/replication_record"}},"created_at":"2026-07-05T07:36:20.943714+00:00","updated_at":"2026-07-05T07:36:20.943714+00:00"}