{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RYUW3X37ZPPH647GDL5W3LE24V","short_pith_number":"pith:RYUW3X37","schema_version":"1.0","canonical_sha256":"8e296ddf7fcbde7f73e61afb6dac9ae56f063610296d73e70385a727947c3b66","source":{"kind":"arxiv","id":"2407.00548","version":2},"attestation_state":"computed","paper":{"title":"KOROL: Learning Visualizable Object Feature with Koopman Operator Rollout for Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abulikemu Abuduweili, Aviral Agrawal, Changliu Liu, Harish Ravichandar, Hongyi Chen, Jeffrey Ichnowski, Yunhai Han","submitted_at":"2024-06-29T23:56:57Z","abstract_excerpt":"Learning dexterous manipulation skills presents significant challenges due to complex nonlinear dynamics that underlie the interactions between objects and multi-fingered hands. Koopman operators have emerged as a robust method for modeling such nonlinear dynamics within a linear framework. However, current methods rely on runtime access to ground-truth (GT) object states, making them unsuitable for vision-based practical applications. Unlike image-to-action policies that implicitly learn visual features for control, we use a dynamics model, specifically the Koopman operator, to learn visually"},"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":"2407.00548","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-06-29T23:56:57Z","cross_cats_sorted":[],"title_canon_sha256":"8fdbff8290addad6af31893279c14eb0b400b7415ed4d3e91fc81bb18276c820","abstract_canon_sha256":"dc9d1ec8ef39d0cbadde51c142865a2878e365982964d8ab3934a9a64f095651"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:37.370331Z","signature_b64":"GDAGv3l+tSfuKWWA/iqLyoa3WorlXwXFt3OeJ+rqbvwU3FFjwbLUQi9KrE3cCakz6/OtHKe01lrFIS3YOc1DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e296ddf7fcbde7f73e61afb6dac9ae56f063610296d73e70385a727947c3b66","last_reissued_at":"2026-07-05T09:04:37.369903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:37.369903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KOROL: Learning Visualizable Object Feature with Koopman Operator Rollout for Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Abulikemu Abuduweili, Aviral Agrawal, Changliu Liu, Harish Ravichandar, Hongyi Chen, Jeffrey Ichnowski, Yunhai Han","submitted_at":"2024-06-29T23:56:57Z","abstract_excerpt":"Learning dexterous manipulation skills presents significant challenges due to complex nonlinear dynamics that underlie the interactions between objects and multi-fingered hands. Koopman operators have emerged as a robust method for modeling such nonlinear dynamics within a linear framework. However, current methods rely on runtime access to ground-truth (GT) object states, making them unsuitable for vision-based practical applications. Unlike image-to-action policies that implicitly learn visual features for control, we use a dynamics model, specifically the Koopman operator, to learn visually"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00548","kind":"arxiv","version":2},"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/2407.00548/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":"2407.00548","created_at":"2026-07-05T09:04:37.369959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00548v2","created_at":"2026-07-05T09:04:37.369959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00548","created_at":"2026-07-05T09:04:37.369959+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYUW3X37ZPPH","created_at":"2026-07-05T09:04:37.369959+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYUW3X37ZPPH647G","created_at":"2026-07-05T09:04:37.369959+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYUW3X37","created_at":"2026-07-05T09:04:37.369959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14321","citing_title":"Continual Learning and Lifting of Koopman Dynamics for Linear Control of Legged Robots","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V","json":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V.json","graph_json":"https://pith.science/api/pith-number/RYUW3X37ZPPH647GDL5W3LE24V/graph.json","events_json":"https://pith.science/api/pith-number/RYUW3X37ZPPH647GDL5W3LE24V/events.json","paper":"https://pith.science/paper/RYUW3X37"},"agent_actions":{"view_html":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V","download_json":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V.json","view_paper":"https://pith.science/paper/RYUW3X37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00548&json=true","fetch_graph":"https://pith.science/api/pith-number/RYUW3X37ZPPH647GDL5W3LE24V/graph.json","fetch_events":"https://pith.science/api/pith-number/RYUW3X37ZPPH647GDL5W3LE24V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V/action/storage_attestation","attest_author":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V/action/author_attestation","sign_citation":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V/action/citation_signature","submit_replication":"https://pith.science/pith/RYUW3X37ZPPH647GDL5W3LE24V/action/replication_record"}},"created_at":"2026-07-05T09:04:37.369959+00:00","updated_at":"2026-07-05T09:04:37.369959+00:00"}