{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WDPOVDCFB2BAQMOQBGONZGQ7S5","short_pith_number":"pith:WDPOVDCF","schema_version":"1.0","canonical_sha256":"b0deea8c450e820831d0099cdc9a1f974c2ffbf72ec53d83c13d2034cc8f1b43","source":{"kind":"arxiv","id":"2504.07092","version":2},"attestation_state":"computed","paper":{"title":"Are We Done with Object-Centric Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Rubinstein, Ameya Prabhu, Matthias Bethge, Seong Joon Oh","submitted_at":"2025-04-09T17:59:05Z","abstract_excerpt":"Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization, sample-efficient composition, and modeling of structured environments. Most research has focused on developing unsupervised mechanisms that separate objects into discrete slots in the representation space, evaluated using unsupervised object discovery. However, with recent sample-efficient segmentation models, we can separate objects in the pixel space and enc"},"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":"2504.07092","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T17:59:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2bbdc9189e31c809906713f7a001d6b58a072e3a5658ecc72477bf91032be685","abstract_canon_sha256":"eff2b8beefb4e482108291d272aa3b3256729ef3ddec310d33a4382334291d66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:39.472657Z","signature_b64":"kImRBoywZemDeLcyWUa84T7GspYY6/EmQ+/gbPQrHYyyhaIwuSL7vTf7swUOk7LI9LoC1cxMomoH1ZjBvWhdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0deea8c450e820831d0099cdc9a1f974c2ffbf72ec53d83c13d2034cc8f1b43","last_reissued_at":"2026-07-05T10:47:39.472147Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:39.472147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are We Done with Object-Centric Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Rubinstein, Ameya Prabhu, Matthias Bethge, Seong Joon Oh","submitted_at":"2025-04-09T17:59:05Z","abstract_excerpt":"Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization, sample-efficient composition, and modeling of structured environments. Most research has focused on developing unsupervised mechanisms that separate objects into discrete slots in the representation space, evaluated using unsupervised object discovery. However, with recent sample-efficient segmentation models, we can separate objects in the pixel space and enc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07092","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/2504.07092/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":"2504.07092","created_at":"2026-07-05T10:47:39.472211+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07092v2","created_at":"2026-07-05T10:47:39.472211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07092","created_at":"2026-07-05T10:47:39.472211+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDPOVDCFB2BA","created_at":"2026-07-05T10:47:39.472211+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDPOVDCFB2BAQMOQ","created_at":"2026-07-05T10:47:39.472211+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDPOVDCF","created_at":"2026-07-05T10:47:39.472211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03976","citing_title":"Formalizing the Binding Problem","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13326","citing_title":"Right Regions, Wrong Labels: Semantic Label Flips in Segmentation under Correlation Shift","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5","json":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5.json","graph_json":"https://pith.science/api/pith-number/WDPOVDCFB2BAQMOQBGONZGQ7S5/graph.json","events_json":"https://pith.science/api/pith-number/WDPOVDCFB2BAQMOQBGONZGQ7S5/events.json","paper":"https://pith.science/paper/WDPOVDCF"},"agent_actions":{"view_html":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5","download_json":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5.json","view_paper":"https://pith.science/paper/WDPOVDCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07092&json=true","fetch_graph":"https://pith.science/api/pith-number/WDPOVDCFB2BAQMOQBGONZGQ7S5/graph.json","fetch_events":"https://pith.science/api/pith-number/WDPOVDCFB2BAQMOQBGONZGQ7S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5/action/storage_attestation","attest_author":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5/action/author_attestation","sign_citation":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5/action/citation_signature","submit_replication":"https://pith.science/pith/WDPOVDCFB2BAQMOQBGONZGQ7S5/action/replication_record"}},"created_at":"2026-07-05T10:47:39.472211+00:00","updated_at":"2026-07-05T10:47:39.472211+00:00"}