{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZGWW2YV5WSVYCGAFRG4L7FLU7E","short_pith_number":"pith:ZGWW2YV5","schema_version":"1.0","canonical_sha256":"c9ad6d62bdb4ab81180589b8bf9574f91989d2bfc4c43a030083a18e42fab3a8","source":{"kind":"arxiv","id":"2206.07764","version":2},"attestation_state":"computed","paper":{"title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aravindh Mahendran, Gamaleldin F. Elsayed, Klaus Greff, Michael C. Mozer, Sjoerd van Steenkiste, Thomas Kipf","submitted_at":"2022-06-15T18:57:07Z","abstract_excerpt":"The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions. Discovering this compositional structure in dynamic visual scenes has proven challenging for end-to-end computer vision approaches unless explicit instance-level supervision is provided. Slot-based models leveraging motion cues have recently shown great promise in learning to represent, segment, and track objects without direct supervision, but they still fail to scale to complex real-world multi-object videos. In an effort to bridge this gap, we take inspiration from human development "},"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":"2206.07764","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-15T18:57:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"89b9d8d2e151bf456724b160486636f21e79508fb743ad76efec9428d1c9409f","abstract_canon_sha256":"5c129a811f67b16ffcd463f5730d4389ed17f24fa534d932cf75131a5f9ec9f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:48.319834Z","signature_b64":"QXLVgs0HyMR8+Ru8TUGNBNXMtR7qsLsOlnW0LiogXdZoma+ca+JfRG8AN22LjvjJG7B9izLQiypBcziY6scFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9ad6d62bdb4ab81180589b8bf9574f91989d2bfc4c43a030083a18e42fab3a8","last_reissued_at":"2026-07-05T05:27:48.319269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:48.319269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aravindh Mahendran, Gamaleldin F. Elsayed, Klaus Greff, Michael C. Mozer, Sjoerd van Steenkiste, Thomas Kipf","submitted_at":"2022-06-15T18:57:07Z","abstract_excerpt":"The visual world can be parsimoniously characterized in terms of distinct entities with sparse interactions. Discovering this compositional structure in dynamic visual scenes has proven challenging for end-to-end computer vision approaches unless explicit instance-level supervision is provided. Slot-based models leveraging motion cues have recently shown great promise in learning to represent, segment, and track objects without direct supervision, but they still fail to scale to complex real-world multi-object videos. In an effort to bridge this gap, we take inspiration from human development "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07764","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.07764/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":"2206.07764","created_at":"2026-07-05T05:27:48.319347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.07764v2","created_at":"2026-07-05T05:27:48.319347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07764","created_at":"2026-07-05T05:27:48.319347+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGWW2YV5WSVY","created_at":"2026-07-05T05:27:48.319347+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGWW2YV5WSVYCGAF","created_at":"2026-07-05T05:27:48.319347+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGWW2YV5","created_at":"2026-07-05T05:27:48.319347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15466","citing_title":"Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15466","citing_title":"Entity-Centric World Models: Interaction-Aware Masking for Causal Video Prediction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E","json":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E.json","graph_json":"https://pith.science/api/pith-number/ZGWW2YV5WSVYCGAFRG4L7FLU7E/graph.json","events_json":"https://pith.science/api/pith-number/ZGWW2YV5WSVYCGAFRG4L7FLU7E/events.json","paper":"https://pith.science/paper/ZGWW2YV5"},"agent_actions":{"view_html":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E","download_json":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E.json","view_paper":"https://pith.science/paper/ZGWW2YV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.07764&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGWW2YV5WSVYCGAFRG4L7FLU7E/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGWW2YV5WSVYCGAFRG4L7FLU7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E/action/storage_attestation","attest_author":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E/action/author_attestation","sign_citation":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E/action/citation_signature","submit_replication":"https://pith.science/pith/ZGWW2YV5WSVYCGAFRG4L7FLU7E/action/replication_record"}},"created_at":"2026-07-05T05:27:48.319347+00:00","updated_at":"2026-07-05T05:27:48.319347+00:00"}