{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YMPQQJFK6ZBOYRIYLHXSNIETAN","short_pith_number":"pith:YMPQQJFK","schema_version":"1.0","canonical_sha256":"c31f0824aaf642ec451859ef26a093037390837893e7a16d364e1de52e38a2f9","source":{"kind":"arxiv","id":"2205.14065","version":1},"attestation_state":"computed","paper":{"title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gautam Singh, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2022-05-27T15:50:44Z","abstract_excerpt":"Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to resolve many critical limitations of traditional single-vector representations such as poor systematic generalization. Although there have been many remarkable advances in recent years, one of the most critical problems in this direction has been that previous methods work only with simple and synthetic scenes but not with complex and naturalistic images or videos. In this paper, we propose STEVE, an unsupervised model for"},"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":"2205.14065","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-27T15:50:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4633736157ce5e16b16124cb42f405fc3877f34181c6f5a832d7b63dbec1fd3e","abstract_canon_sha256":"dfe9b8d65b78a92be6f3c64740bb5db0966d98a332b78a5a7cba9c8a7244e5ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:01.105934Z","signature_b64":"lilPk1CvlCWQEBVxQXDA7WSaEKnRcYRIvG9z1t8hm1B5uGpr66B8pfhI7lK3vFgRyCc0DUy0eIVl8Gkg8/sKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c31f0824aaf642ec451859ef26a093037390837893e7a16d364e1de52e38a2f9","last_reissued_at":"2026-07-05T04:27:01.105475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:01.105475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Gautam Singh, Sungjin Ahn, Yi-Fu Wu","submitted_at":"2022-05-27T15:50:44Z","abstract_excerpt":"Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to resolve many critical limitations of traditional single-vector representations such as poor systematic generalization. Although there have been many remarkable advances in recent years, one of the most critical problems in this direction has been that previous methods work only with simple and synthetic scenes but not with complex and naturalistic images or videos. In this paper, we propose STEVE, an unsupervised model for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14065","kind":"arxiv","version":1},"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/2205.14065/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":"2205.14065","created_at":"2026-07-05T04:27:01.105533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14065v1","created_at":"2026-07-05T04:27:01.105533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14065","created_at":"2026-07-05T04:27:01.105533+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMPQQJFK6ZBO","created_at":"2026-07-05T04:27:01.105533+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMPQQJFK6ZBOYRIY","created_at":"2026-07-05T04:27:01.105533+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMPQQJFK","created_at":"2026-07-05T04:27:01.105533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":237,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN","json":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN.json","graph_json":"https://pith.science/api/pith-number/YMPQQJFK6ZBOYRIYLHXSNIETAN/graph.json","events_json":"https://pith.science/api/pith-number/YMPQQJFK6ZBOYRIYLHXSNIETAN/events.json","paper":"https://pith.science/paper/YMPQQJFK"},"agent_actions":{"view_html":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN","download_json":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN.json","view_paper":"https://pith.science/paper/YMPQQJFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14065&json=true","fetch_graph":"https://pith.science/api/pith-number/YMPQQJFK6ZBOYRIYLHXSNIETAN/graph.json","fetch_events":"https://pith.science/api/pith-number/YMPQQJFK6ZBOYRIYLHXSNIETAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN/action/storage_attestation","attest_author":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN/action/author_attestation","sign_citation":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN/action/citation_signature","submit_replication":"https://pith.science/pith/YMPQQJFK6ZBOYRIYLHXSNIETAN/action/replication_record"}},"created_at":"2026-07-05T04:27:01.105533+00:00","updated_at":"2026-07-05T04:27:01.105533+00:00"}