{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3GEBGARNL2OPI7IBF2AYO3KEBP","short_pith_number":"pith:3GEBGARN","schema_version":"1.0","canonical_sha256":"d98813022d5e9cf47d012e81876d440bf44581008204a0b1814ebc31f1db983d","source":{"kind":"arxiv","id":"1906.03853","version":2},"attestation_state":"computed","paper":{"title":"DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Jiajun Wu, Joshua B. Tenenbaum, Shuran Song, Zhenjia Xu","submitted_at":"2019-06-10T09:13:02Z","abstract_excerpt":"We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the object's static appearance. In this paper, we propose DensePhysNet, a system that actively executes a sequence of dynamic interactions (e.g., sliding and colliding), and uses a deep predictive model over its visual observations to learn dense, pixel-wise representations that reflect the physical properties of observed objects. Our experiments i"},"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":"1906.03853","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-06-10T09:13:02Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"111fdd4dac7893fcaf0d719512b235aea7a368406e857873001a1513f23be57b","abstract_canon_sha256":"5bf2c15ce9e136b0848ab06236de9b9a0688b88de72e0ae9d0115a1eb7d3b47b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.452972Z","signature_b64":"mIqwtzfUFeCEa9uc/S0k1MVuMrRpzqjGN4s/kfJuzc7oaCrBG4Y592P2RCH/NNXI93TVODUTgoIPh7VYb6+xDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d98813022d5e9cf47d012e81876d440bf44581008204a0b1814ebc31f1db983d","last_reissued_at":"2026-05-17T23:43:32.452557Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.452557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DensePhysNet: Learning Dense Physical Object Representations via Multi-step Dynamic Interactions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andy Zeng, Jiajun Wu, Joshua B. Tenenbaum, Shuran Song, Zhenjia Xu","submitted_at":"2019-06-10T09:13:02Z","abstract_excerpt":"We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the object's static appearance. In this paper, we propose DensePhysNet, a system that actively executes a sequence of dynamic interactions (e.g., sliding and colliding), and uses a deep predictive model over its visual observations to learn dense, pixel-wise representations that reflect the physical properties of observed objects. Our experiments i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03853","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":""},"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":"1906.03853","created_at":"2026-05-17T23:43:32.452618+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.03853v2","created_at":"2026-05-17T23:43:32.452618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03853","created_at":"2026-05-17T23:43:32.452618+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GEBGARNL2OP","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GEBGARNL2OPI7IB","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GEBGARN","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2506.05317","citing_title":"ProJo4D: Progressive Joint Optimization for Sparse-View Inverse Physics Estimation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21998","citing_title":"Causal World Modeling for Robot Control","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP","json":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP.json","graph_json":"https://pith.science/api/pith-number/3GEBGARNL2OPI7IBF2AYO3KEBP/graph.json","events_json":"https://pith.science/api/pith-number/3GEBGARNL2OPI7IBF2AYO3KEBP/events.json","paper":"https://pith.science/paper/3GEBGARN"},"agent_actions":{"view_html":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP","download_json":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP.json","view_paper":"https://pith.science/paper/3GEBGARN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.03853&json=true","fetch_graph":"https://pith.science/api/pith-number/3GEBGARNL2OPI7IBF2AYO3KEBP/graph.json","fetch_events":"https://pith.science/api/pith-number/3GEBGARNL2OPI7IBF2AYO3KEBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP/action/storage_attestation","attest_author":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP/action/author_attestation","sign_citation":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP/action/citation_signature","submit_replication":"https://pith.science/pith/3GEBGARNL2OPI7IBF2AYO3KEBP/action/replication_record"}},"created_at":"2026-05-17T23:43:32.452618+00:00","updated_at":"2026-05-17T23:43:32.452618+00:00"}