{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CSQJKELEPI2RQVKZFNQIE2X4BD","short_pith_number":"pith:CSQJKELE","schema_version":"1.0","canonical_sha256":"14a09511647a351855592b60826afc08e59a9894f9a573681be53a54dc4b3331","source":{"kind":"arxiv","id":"2103.04301","version":3},"attestation_state":"computed","paper":{"title":"DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrew Zhao, Haipeng Zhang, Hao Dong, Haoqi Yuan, Ruihai Wu, Zihan Ding","submitted_at":"2021-03-07T08:42:33Z","abstract_excerpt":"Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labelled actions, object entities or locations, which can be demanding in many cases. To cope with this limitation, we propose a method, dubbed DMotion, that trains a forward model from video data only, via disentangling the motion of controllable agent to model the transition dynamics. An object extractor and an interaction learner are trained in an end-to-end manner without supervision. The agent's motions are explicitly"},"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":"2103.04301","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-03-07T08:42:33Z","cross_cats_sorted":[],"title_canon_sha256":"a4c71779c9992e709d2ba96c80012f8e1c758bfbae02dc245c85601546bdcefa","abstract_canon_sha256":"4158b3850a694ce78c73457002d10b49de5498175b8c84a9767d1f558291be61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:32.069832Z","signature_b64":"jVH+tO7VRg1KEXpfPDjx6JztnMdlVapOG7J0395TO3xwJRgx0SUEkMyX/Mv+LAXfJzUT0duz6JL16uGg+itvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14a09511647a351855592b60826afc08e59a9894f9a573681be53a54dc4b3331","last_reissued_at":"2026-07-05T03:00:32.069339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:32.069339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DMotion: Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Andrew Zhao, Haipeng Zhang, Hao Dong, Haoqi Yuan, Ruihai Wu, Zihan Ding","submitted_at":"2021-03-07T08:42:33Z","abstract_excerpt":"Learning an accurate model of the environment is essential for model-based control tasks. Existing methods in robotic visuomotor control usually learn from data with heavily labelled actions, object entities or locations, which can be demanding in many cases. To cope with this limitation, we propose a method, dubbed DMotion, that trains a forward model from video data only, via disentangling the motion of controllable agent to model the transition dynamics. An object extractor and an interaction learner are trained in an end-to-end manner without supervision. The agent's motions are explicitly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04301","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/2103.04301/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":"2103.04301","created_at":"2026-07-05T03:00:32.069403+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.04301v3","created_at":"2026-07-05T03:00:32.069403+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04301","created_at":"2026-07-05T03:00:32.069403+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSQJKELEPI2R","created_at":"2026-07-05T03:00:32.069403+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSQJKELEPI2RQVKZ","created_at":"2026-07-05T03:00:32.069403+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSQJKELE","created_at":"2026-07-05T03:00:32.069403+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/CSQJKELEPI2RQVKZFNQIE2X4BD","json":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD.json","graph_json":"https://pith.science/api/pith-number/CSQJKELEPI2RQVKZFNQIE2X4BD/graph.json","events_json":"https://pith.science/api/pith-number/CSQJKELEPI2RQVKZFNQIE2X4BD/events.json","paper":"https://pith.science/paper/CSQJKELE"},"agent_actions":{"view_html":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD","download_json":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD.json","view_paper":"https://pith.science/paper/CSQJKELE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.04301&json=true","fetch_graph":"https://pith.science/api/pith-number/CSQJKELEPI2RQVKZFNQIE2X4BD/graph.json","fetch_events":"https://pith.science/api/pith-number/CSQJKELEPI2RQVKZFNQIE2X4BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD/action/storage_attestation","attest_author":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD/action/author_attestation","sign_citation":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD/action/citation_signature","submit_replication":"https://pith.science/pith/CSQJKELEPI2RQVKZFNQIE2X4BD/action/replication_record"}},"created_at":"2026-07-05T03:00:32.069403+00:00","updated_at":"2026-07-05T03:00:32.069403+00:00"}