{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D4OQWF5VTCOPFTT5UKIMOFL2GE","short_pith_number":"pith:D4OQWF5V","schema_version":"1.0","canonical_sha256":"1f1d0b17b5989cf2ce7da290c7157a313c67b8cb204207751c58e8b174ed5702","source":{"kind":"arxiv","id":"2411.01284","version":1},"attestation_state":"computed","paper":{"title":"Task-Oriented Hierarchical Object Decomposition for Visuomotor Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bernadette Bucher, Dinesh Jayaraman, Jianing Qian, Yunshuang Li","submitted_at":"2024-11-02T15:28:06Z","abstract_excerpt":"Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, these representations cannot effectively ignore any task-irrelevant information in the scene, and (2) They often lack the representational capacity to handle unconstrained/complex real-world scenes. Instead, we propose to train a large combinatorial family of representations organized by scene entities: objects and object parts. This hierarchical 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":"2411.01284","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-02T15:28:06Z","cross_cats_sorted":[],"title_canon_sha256":"9daf964238a3e0b7c7107fdf03936f3e5372194c92618c6dee785bf6a1c5eb3a","abstract_canon_sha256":"cc63f6bad8516dbbcb38986a46a07af3184810d8c90b0022436384c4d219e835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:27.943227Z","signature_b64":"m2/rByBSo8iH+5hOXjqIAANK9bXqSwb+vUIXTIiWIOPeMdZBc4DSvnXsIbLBfxVUEKIj3K0wFQJdTF4MneaFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f1d0b17b5989cf2ce7da290c7157a313c67b8cb204207751c58e8b174ed5702","last_reissued_at":"2026-07-05T09:30:27.942783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:27.942783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Oriented Hierarchical Object Decomposition for Visuomotor Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Bernadette Bucher, Dinesh Jayaraman, Jianing Qian, Yunshuang Li","submitted_at":"2024-11-02T15:28:06Z","abstract_excerpt":"Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, these representations cannot effectively ignore any task-irrelevant information in the scene, and (2) They often lack the representational capacity to handle unconstrained/complex real-world scenes. Instead, we propose to train a large combinatorial family of representations organized by scene entities: objects and object parts. This hierarchical ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01284","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/2411.01284/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":"2411.01284","created_at":"2026-07-05T09:30:27.942839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01284v1","created_at":"2026-07-05T09:30:27.942839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01284","created_at":"2026-07-05T09:30:27.942839+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4OQWF5VTCOP","created_at":"2026-07-05T09:30:27.942839+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4OQWF5VTCOPFTT5","created_at":"2026-07-05T09:30:27.942839+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4OQWF5V","created_at":"2026-07-05T09:30:27.942839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15455","citing_title":"One-Shot Cross-Geometry Skill Transfer through Part Decomposition","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE","json":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE.json","graph_json":"https://pith.science/api/pith-number/D4OQWF5VTCOPFTT5UKIMOFL2GE/graph.json","events_json":"https://pith.science/api/pith-number/D4OQWF5VTCOPFTT5UKIMOFL2GE/events.json","paper":"https://pith.science/paper/D4OQWF5V"},"agent_actions":{"view_html":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE","download_json":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE.json","view_paper":"https://pith.science/paper/D4OQWF5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01284&json=true","fetch_graph":"https://pith.science/api/pith-number/D4OQWF5VTCOPFTT5UKIMOFL2GE/graph.json","fetch_events":"https://pith.science/api/pith-number/D4OQWF5VTCOPFTT5UKIMOFL2GE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE/action/storage_attestation","attest_author":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE/action/author_attestation","sign_citation":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE/action/citation_signature","submit_replication":"https://pith.science/pith/D4OQWF5VTCOPFTT5UKIMOFL2GE/action/replication_record"}},"created_at":"2026-07-05T09:30:27.942839+00:00","updated_at":"2026-07-05T09:30:27.942839+00:00"}