{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K7RIGKHYIZMHSSGXFXBNVV7ULP","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":"ad23d5839ccd2927c1733c3e2fabc981b7be16928de76a09cd878e9e4d65ce80","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-27T17:55:13Z","title_canon_sha256":"a99e69639e7a5eb5beb568d761080162bddce51082c05ba2a67f828498ea601f"},"schema_version":"1.0","source":{"id":"2304.14391","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14391","created_at":"2026-07-05T07:36:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14391v4","created_at":"2026-07-05T07:36:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14391","created_at":"2026-07-05T07:36:20Z"},{"alias_kind":"pith_short_12","alias_value":"K7RIGKHYIZMH","created_at":"2026-07-05T07:36:20Z"},{"alias_kind":"pith_short_16","alias_value":"K7RIGKHYIZMHSSGX","created_at":"2026-07-05T07:36:20Z"},{"alias_kind":"pith_short_8","alias_value":"K7RIGKHY","created_at":"2026-07-05T07:36:20Z"}],"graph_snapshots":[{"event_id":"sha256:19781f90f9e7e26e658470998c8c4573b118138a8629af5c879a6ac07efcd30a","target":"graph","created_at":"2026-07-05T07:36:20Z","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/2304.14391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ayush Jain, Christopher Atkeson, Katerina Fragkiadaki, Nikolaos Gkanatsios, Yunchu Zhang, Zhou Xian","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-27T17:55:13Z","title":"Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14391","kind":"arxiv","version":4},"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:c3c68ec534982acef9c5cb873867fb4384ea26c2a1b04cf40993c6f38a9f57a2","target":"record","created_at":"2026-07-05T07:36:20Z","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":"ad23d5839ccd2927c1733c3e2fabc981b7be16928de76a09cd878e9e4d65ce80","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2023-04-27T17:55:13Z","title_canon_sha256":"a99e69639e7a5eb5beb568d761080162bddce51082c05ba2a67f828498ea601f"},"schema_version":"1.0","source":{"id":"2304.14391","kind":"arxiv","version":4}},"canonical_sha256":"57e28328f846587948d72dc2dad7f45be371a488b3141235da47c5a32da43fd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57e28328f846587948d72dc2dad7f45be371a488b3141235da47c5a32da43fd9","first_computed_at":"2026-07-05T07:36:20.943659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:20.943659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eqBLsvr/0XD7rtMafk5BjS2lJy8C5mL6SFYvDZ2j0syuLdZ9gMyWTcc+sCqqkditG4GNbaVEfjZMMrM5y8YBCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:20.944077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14391","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3c68ec534982acef9c5cb873867fb4384ea26c2a1b04cf40993c6f38a9f57a2","sha256:19781f90f9e7e26e658470998c8c4573b118138a8629af5c879a6ac07efcd30a"],"state_sha256":"15c0f99b04b8fe2a3d2209d7d5eca06c1030db99b9913e450f7e5fae4032272e"}