{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T55ZBP4EZJ5ML23M6E6O7BSMIL","short_pith_number":"pith:T55ZBP4E","schema_version":"1.0","canonical_sha256":"9f7b90bf84ca7ac5eb6cf13cef864c42db62fd07cc3c0cb36004a6308ea30623","source":{"kind":"arxiv","id":"2102.02493","version":3},"attestation_state":"computed","paper":{"title":"Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dmitry Berenson, Thomas Power","submitted_at":"2021-02-04T09:08:50Z","abstract_excerpt":"When manipulating a novel object with complex dynamics, a state representation is not always available, for example for deformable objects. Learning both a representation and dynamics from observations requires large amounts of data. We propose Learned Visual Similarity Predictive Control (LVSPC), a novel method for data-efficient learning to control systems with complex dynamics and high-dimensional state spaces from images. LVSPC leverages a given simple model approximation from which image observations can be generated. We use these images to train a perception model that estimates the simp"},"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":"2102.02493","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-04T09:08:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"943331527fe00740f81b2c32bb969938b16a05a67c327565443080a09eb4a4f4","abstract_canon_sha256":"2577650198fbfb314c2cfe7b1e20e32602c2ca9e49ba6b02d8ef923eb71f5736"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:01.769337Z","signature_b64":"Zb7Ot13JZVnQ3QmXlU6fhnyh83zDqE9wb1O+pQdUFgFKOdCqRI9rpwDoQF0N0ZARwDUw05JhJvAWl20ir9RsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f7b90bf84ca7ac5eb6cf13cef864c42db62fd07cc3c0cb36004a6308ea30623","last_reissued_at":"2026-07-05T02:16:01.768803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:01.768803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Dmitry Berenson, Thomas Power","submitted_at":"2021-02-04T09:08:50Z","abstract_excerpt":"When manipulating a novel object with complex dynamics, a state representation is not always available, for example for deformable objects. Learning both a representation and dynamics from observations requires large amounts of data. We propose Learned Visual Similarity Predictive Control (LVSPC), a novel method for data-efficient learning to control systems with complex dynamics and high-dimensional state spaces from images. LVSPC leverages a given simple model approximation from which image observations can be generated. We use these images to train a perception model that estimates the simp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02493","kind":"arxiv","version":3},"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/2102.02493/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":"2102.02493","created_at":"2026-07-05T02:16:01.768874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.02493v3","created_at":"2026-07-05T02:16:01.768874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02493","created_at":"2026-07-05T02:16:01.768874+00:00"},{"alias_kind":"pith_short_12","alias_value":"T55ZBP4EZJ5M","created_at":"2026-07-05T02:16:01.768874+00:00"},{"alias_kind":"pith_short_16","alias_value":"T55ZBP4EZJ5ML23M","created_at":"2026-07-05T02:16:01.768874+00:00"},{"alias_kind":"pith_short_8","alias_value":"T55ZBP4E","created_at":"2026-07-05T02:16:01.768874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04645","citing_title":"Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL","json":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL.json","graph_json":"https://pith.science/api/pith-number/T55ZBP4EZJ5ML23M6E6O7BSMIL/graph.json","events_json":"https://pith.science/api/pith-number/T55ZBP4EZJ5ML23M6E6O7BSMIL/events.json","paper":"https://pith.science/paper/T55ZBP4E"},"agent_actions":{"view_html":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL","download_json":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL.json","view_paper":"https://pith.science/paper/T55ZBP4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.02493&json=true","fetch_graph":"https://pith.science/api/pith-number/T55ZBP4EZJ5ML23M6E6O7BSMIL/graph.json","fetch_events":"https://pith.science/api/pith-number/T55ZBP4EZJ5ML23M6E6O7BSMIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL/action/storage_attestation","attest_author":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL/action/author_attestation","sign_citation":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL/action/citation_signature","submit_replication":"https://pith.science/pith/T55ZBP4EZJ5ML23M6E6O7BSMIL/action/replication_record"}},"created_at":"2026-07-05T02:16:01.768874+00:00","updated_at":"2026-07-05T02:16:01.768874+00:00"}