{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MOEAJTSZZED7HP2BPZPBDH27IX","short_pith_number":"pith:MOEAJTSZ","schema_version":"1.0","canonical_sha256":"638804ce59c907f3bf417e5e119f5f45c11db6fa2742f70b5074aa15ccd85cc3","source":{"kind":"arxiv","id":"1907.13052","version":4},"attestation_state":"computed","paper":{"title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam R. Kosiorek, Ingmar Posner, Martin Engelcke, Oiwi Parker Jones","submitted_at":"2019-07-30T16:22:39Z","abstract_excerpt":"Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centri"},"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":"1907.13052","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-30T16:22:39Z","cross_cats_sorted":["cs.CV","cs.NE","cs.RO","stat.ML"],"title_canon_sha256":"971c1af61786ade5c5f61f92c8052b565e4b9c7c3c8b78e7c948e77d4e227d72","abstract_canon_sha256":"71db099937b19e4a215776753d42d7df64f341c992ea0731ad2abcdc81d182c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:36.026300Z","signature_b64":"b4Ii8o+bco6krCa1bDHXVn3bsEb/KqvvA+vCb6gZ35kzTNd4y5ISu+wJ7i5c+CUFnziiGLflAcGBgUKwad0TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"638804ce59c907f3bf417e5e119f5f45c11db6fa2742f70b5074aa15ccd85cc3","last_reissued_at":"2026-07-05T01:53:36.025790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:36.025790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam R. Kosiorek, Ingmar Posner, Martin Engelcke, Oiwi Parker Jones","submitted_at":"2019-07-30T16:22:39Z","abstract_excerpt":"Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.13052","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/1907.13052/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":"1907.13052","created_at":"2026-07-05T01:53:36.025851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.13052v4","created_at":"2026-07-05T01:53:36.025851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13052","created_at":"2026-07-05T01:53:36.025851+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOEAJTSZZED7","created_at":"2026-07-05T01:53:36.025851+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOEAJTSZZED7HP2B","created_at":"2026-07-05T01:53:36.025851+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOEAJTSZ","created_at":"2026-07-05T01:53:36.025851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05319","citing_title":"Steering Optimisation Trajectories in Diffusion Representation Learning","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":195,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX","json":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX.json","graph_json":"https://pith.science/api/pith-number/MOEAJTSZZED7HP2BPZPBDH27IX/graph.json","events_json":"https://pith.science/api/pith-number/MOEAJTSZZED7HP2BPZPBDH27IX/events.json","paper":"https://pith.science/paper/MOEAJTSZ"},"agent_actions":{"view_html":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX","download_json":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX.json","view_paper":"https://pith.science/paper/MOEAJTSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.13052&json=true","fetch_graph":"https://pith.science/api/pith-number/MOEAJTSZZED7HP2BPZPBDH27IX/graph.json","fetch_events":"https://pith.science/api/pith-number/MOEAJTSZZED7HP2BPZPBDH27IX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX/action/storage_attestation","attest_author":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX/action/author_attestation","sign_citation":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX/action/citation_signature","submit_replication":"https://pith.science/pith/MOEAJTSZZED7HP2BPZPBDH27IX/action/replication_record"}},"created_at":"2026-07-05T01:53:36.025851+00:00","updated_at":"2026-07-05T01:53:36.025851+00:00"}