{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZDVPMZCPC4KPJ33PVLO7YEVJ7","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":"54340131e119d1e8da6a99ac7a8921b1981eede885649ac5432f91bda9e5a95f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-13T22:15:31Z","title_canon_sha256":"21d287c0a2b237b3d6df45df56e99a2163f61fb31b6bd3f98426c4bde2465695"},"schema_version":"1.0","source":{"id":"2411.09052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09052","created_at":"2026-07-05T09:35:19Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09052v1","created_at":"2026-07-05T09:35:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09052","created_at":"2026-07-05T09:35:19Z"},{"alias_kind":"pith_short_12","alias_value":"AZDVPMZCPC4K","created_at":"2026-07-05T09:35:19Z"},{"alias_kind":"pith_short_16","alias_value":"AZDVPMZCPC4KPJ33","created_at":"2026-07-05T09:35:19Z"},{"alias_kind":"pith_short_8","alias_value":"AZDVPMZC","created_at":"2026-07-05T09:35:19Z"}],"graph_snapshots":[{"event_id":"sha256:46cb738f0b2f6e8bfb451e1fee8185b149fd82b0d3775ea9b339437fe5937d26","target":"graph","created_at":"2026-07-05T09:35:19Z","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/2411.09052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robotics tasks are highly compositional by nature. For example, to perform a high-level task like cleaning the table a robot must employ low-level capabilities of moving the effectors to the objects on the table, pick them up and then move them off the table one-by-one, while re-evaluating the consequently dynamic scenario in the process. Given that large vision language models (VLMs) have shown progress on many tasks that require high level, human-like reasoning, we ask the question: if the models are taught the requisite low-level capabilities, can they compose them in novel ways to achieve ","authors_text":"Apratim Bhattacharyya, Daniel Dijkman, Roland Memisevic, Sanjay Haresh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-13T22:15:31Z","title":"ClevrSkills: Compositional Language and Visual Reasoning in Robotics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09052","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":"sha256:5b1eed56283ca1ad3d953925d2f65dae75209db1671b7783bedeaab0ca5d592a","target":"record","created_at":"2026-07-05T09:35:19Z","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":"54340131e119d1e8da6a99ac7a8921b1981eede885649ac5432f91bda9e5a95f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-13T22:15:31Z","title_canon_sha256":"21d287c0a2b237b3d6df45df56e99a2163f61fb31b6bd3f98426c4bde2465695"},"schema_version":"1.0","source":{"id":"2411.09052","kind":"arxiv","version":1}},"canonical_sha256":"064757b32278b8a7a77b7d56efe0954fcd9994e38c508778a5451165f887c0aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"064757b32278b8a7a77b7d56efe0954fcd9994e38c508778a5451165f887c0aa","first_computed_at":"2026-07-05T09:35:19.036401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:19.036401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C/scYSv+uDAayc3VraBnUXmBrYkPFgksVHqvFjXod10JBjjTzEQJ6AUyV83qKbgF7wxivq2tidJ7M3eeeSFmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:19.036911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b1eed56283ca1ad3d953925d2f65dae75209db1671b7783bedeaab0ca5d592a","sha256:46cb738f0b2f6e8bfb451e1fee8185b149fd82b0d3775ea9b339437fe5937d26"],"state_sha256":"1d309bde314f7c4b68d3845a4d3fca3ec01cfb4218338b907d70cb4e9be19e39"}