{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AZDVPMZCPC4KPJ33PVLO7YEVJ7","short_pith_number":"pith:AZDVPMZC","schema_version":"1.0","canonical_sha256":"064757b32278b8a7a77b7d56efe0954fcd9994e38c508778a5451165f887c0aa","source":{"kind":"arxiv","id":"2411.09052","version":1},"attestation_state":"computed","paper":{"title":"ClevrSkills: Compositional Language and Visual Reasoning in Robotics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Apratim Bhattacharyya, Daniel Dijkman, Roland Memisevic, Sanjay Haresh","submitted_at":"2024-11-13T22:15:31Z","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 "},"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":"2411.09052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-13T22:15:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"21d287c0a2b237b3d6df45df56e99a2163f61fb31b6bd3f98426c4bde2465695","abstract_canon_sha256":"54340131e119d1e8da6a99ac7a8921b1981eede885649ac5432f91bda9e5a95f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:35:19.036911Z","signature_b64":"C/scYSv+uDAayc3VraBnUXmBrYkPFgksVHqvFjXod10JBjjTzEQJ6AUyV83qKbgF7wxivq2tidJ7M3eeeSFmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"064757b32278b8a7a77b7d56efe0954fcd9994e38c508778a5451165f887c0aa","last_reissued_at":"2026-07-05T09:35:19.036401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:35:19.036401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClevrSkills: Compositional Language and Visual Reasoning in Robotics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Apratim Bhattacharyya, Daniel Dijkman, Roland Memisevic, Sanjay Haresh","submitted_at":"2024-11-13T22:15:31Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09052","kind":"arxiv","version":1},"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/2411.09052/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":"2411.09052","created_at":"2026-07-05T09:35:19.036471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09052v1","created_at":"2026-07-05T09:35:19.036471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09052","created_at":"2026-07-05T09:35:19.036471+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZDVPMZCPC4K","created_at":"2026-07-05T09:35:19.036471+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZDVPMZCPC4KPJ33","created_at":"2026-07-05T09:35:19.036471+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZDVPMZC","created_at":"2026-07-05T09:35:19.036471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7","json":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7.json","graph_json":"https://pith.science/api/pith-number/AZDVPMZCPC4KPJ33PVLO7YEVJ7/graph.json","events_json":"https://pith.science/api/pith-number/AZDVPMZCPC4KPJ33PVLO7YEVJ7/events.json","paper":"https://pith.science/paper/AZDVPMZC"},"agent_actions":{"view_html":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7","download_json":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7.json","view_paper":"https://pith.science/paper/AZDVPMZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09052&json=true","fetch_graph":"https://pith.science/api/pith-number/AZDVPMZCPC4KPJ33PVLO7YEVJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/AZDVPMZCPC4KPJ33PVLO7YEVJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7/action/storage_attestation","attest_author":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7/action/author_attestation","sign_citation":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7/action/citation_signature","submit_replication":"https://pith.science/pith/AZDVPMZCPC4KPJ33PVLO7YEVJ7/action/replication_record"}},"created_at":"2026-07-05T09:35:19.036471+00:00","updated_at":"2026-07-05T09:35:19.036471+00:00"}