{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KMTMRSCYIN4KWP3O2SQ2FA4GY2","short_pith_number":"pith:KMTMRSCY","schema_version":"1.0","canonical_sha256":"5326c8c8584378ab3f6ed4a1a28386c6a2b60fb9de9c89c77fa3f11114c3d5e2","source":{"kind":"arxiv","id":"1904.07482","version":4},"attestation_state":"computed","paper":{"title":"Object-Oriented Dynamics Learning through Multi-Level Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Guangxiang Zhu, Jianhao Wang, Zhizhou Ren, Zichuan Lin","submitted_at":"2019-04-16T06:01:17Z","abstract_excerpt":"Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-supervised learning framework, called Multi-level Abstraction Object-oriented Predictor (MAOP), which employs a three-level learning architecture that enables efficient object-based dynamics learning from raw visual observations. We also design a spatial-temporal relational reason"},"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":"1904.07482","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-16T06:01:17Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"8fb3658873efbdb3128728a161a876036e2ebd591b22db6f77a3226c8865decb","abstract_canon_sha256":"6e606b98cff09c67d27c2741a8318caddc9fd4d9fa46d29dfef77128859c2c95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:07.229086Z","signature_b64":"KszPnN1SeBAhEbJk4FZ7+CxiMTUN0QBdE2H3K2wEq0WwzVuib6ICKRu+weT26suIs8NadITRrcf20V7pwa8YCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5326c8c8584378ab3f6ed4a1a28386c6a2b60fb9de9c89c77fa3f11114c3d5e2","last_reissued_at":"2026-07-05T00:24:07.228595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:07.228595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Oriented Dynamics Learning through Multi-Level Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Guangxiang Zhu, Jianhao Wang, Zhizhou Ren, Zichuan Lin","submitted_at":"2019-04-16T06:01:17Z","abstract_excerpt":"Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with multiple dynamic objects. In this paper, we present a novel self-supervised learning framework, called Multi-level Abstraction Object-oriented Predictor (MAOP), which employs a three-level learning architecture that enables efficient object-based dynamics learning from raw visual observations. We also design a spatial-temporal relational reason"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07482","kind":"arxiv","version":4},"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/1904.07482/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":"1904.07482","created_at":"2026-07-05T00:24:07.228654+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07482v4","created_at":"2026-07-05T00:24:07.228654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07482","created_at":"2026-07-05T00:24:07.228654+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMTMRSCYIN4K","created_at":"2026-07-05T00:24:07.228654+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMTMRSCYIN4KWP3O","created_at":"2026-07-05T00:24:07.228654+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMTMRSCY","created_at":"2026-07-05T00:24:07.228654+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/KMTMRSCYIN4KWP3O2SQ2FA4GY2","json":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2.json","graph_json":"https://pith.science/api/pith-number/KMTMRSCYIN4KWP3O2SQ2FA4GY2/graph.json","events_json":"https://pith.science/api/pith-number/KMTMRSCYIN4KWP3O2SQ2FA4GY2/events.json","paper":"https://pith.science/paper/KMTMRSCY"},"agent_actions":{"view_html":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2","download_json":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2.json","view_paper":"https://pith.science/paper/KMTMRSCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07482&json=true","fetch_graph":"https://pith.science/api/pith-number/KMTMRSCYIN4KWP3O2SQ2FA4GY2/graph.json","fetch_events":"https://pith.science/api/pith-number/KMTMRSCYIN4KWP3O2SQ2FA4GY2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2/action/storage_attestation","attest_author":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2/action/author_attestation","sign_citation":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2/action/citation_signature","submit_replication":"https://pith.science/pith/KMTMRSCYIN4KWP3O2SQ2FA4GY2/action/replication_record"}},"created_at":"2026-07-05T00:24:07.228654+00:00","updated_at":"2026-07-05T00:24:07.228654+00:00"}