{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3RCRDNWJ7HR2ZJJYT5UKL2PBGL","short_pith_number":"pith:3RCRDNWJ","schema_version":"1.0","canonical_sha256":"dc4511b6c9f9e3aca5389f68a5e9e132fc232ebacfc1c7a8e877c5326362fba5","source":{"kind":"arxiv","id":"2011.06813","version":1},"attestation_state":"computed","paper":{"title":"Learning Object Manipulation Skills via Approximate State Estimation from Real Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ivan Laptev, Josef Sivic, Makarand Tapaswi, Vladim\\'ir Petr\\'ik","submitted_at":"2020-11-13T08:53:47Z","abstract_excerpt":"Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain. In this paper, we explore a method that facilitates learning object manipulation skills directly from videos. Leveraging recent advances in 2D visual recognition and differentiable rendering, we develop an optimization based method to estimate a coarse 3D state representation for the hand and the manipulated object(s) without requiring any supervision. "},"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":"2011.06813","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-13T08:53:47Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7d780e0021598beba836783dd910a39caca53e053a7c3c82512acec006ee9700","abstract_canon_sha256":"1669e0a65e128e2ad9d168be77e756c40c1a05ba039ea849140298217cd3f15f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:25.258027Z","signature_b64":"f5PgoSzbnxJPEFgL5ZDDfvXs4fJ3DT0r9QacANvLBF/cU10rGc78VUwzJ0ShwlH9EbLwNipTpcJzB3tyGNhFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4511b6c9f9e3aca5389f68a5e9e132fc232ebacfc1c7a8e877c5326362fba5","last_reissued_at":"2026-07-05T01:51:25.257693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:25.257693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Object Manipulation Skills via Approximate State Estimation from Real Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Ivan Laptev, Josef Sivic, Makarand Tapaswi, Vladim\\'ir Petr\\'ik","submitted_at":"2020-11-13T08:53:47Z","abstract_excerpt":"Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain. In this paper, we explore a method that facilitates learning object manipulation skills directly from videos. Leveraging recent advances in 2D visual recognition and differentiable rendering, we develop an optimization based method to estimate a coarse 3D state representation for the hand and the manipulated object(s) without requiring any supervision. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06813","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/2011.06813/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":"2011.06813","created_at":"2026-07-05T01:51:25.257748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06813v1","created_at":"2026-07-05T01:51:25.257748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06813","created_at":"2026-07-05T01:51:25.257748+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RCRDNWJ7HR2","created_at":"2026-07-05T01:51:25.257748+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RCRDNWJ7HR2ZJJY","created_at":"2026-07-05T01:51:25.257748+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RCRDNWJ","created_at":"2026-07-05T01:51:25.257748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL","json":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL.json","graph_json":"https://pith.science/api/pith-number/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/graph.json","events_json":"https://pith.science/api/pith-number/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/events.json","paper":"https://pith.science/paper/3RCRDNWJ"},"agent_actions":{"view_html":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL","download_json":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL.json","view_paper":"https://pith.science/paper/3RCRDNWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06813&json=true","fetch_graph":"https://pith.science/api/pith-number/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/graph.json","fetch_events":"https://pith.science/api/pith-number/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/action/storage_attestation","attest_author":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/action/author_attestation","sign_citation":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/action/citation_signature","submit_replication":"https://pith.science/pith/3RCRDNWJ7HR2ZJJYT5UKL2PBGL/action/replication_record"}},"created_at":"2026-07-05T01:51:25.257748+00:00","updated_at":"2026-07-05T01:51:25.257748+00:00"}