{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GWTJDFN6C5MVA6ZGDLYP7BOJAZ","short_pith_number":"pith:GWTJDFN6","schema_version":"1.0","canonical_sha256":"35a69195be1759507b261af0ff85c906563c7631b394de7067109137b7dc5525","source":{"kind":"arxiv","id":"2310.05327","version":2},"attestation_state":"computed","paper":{"title":"Provable Compositional Generalization for Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Panfilov, Attila Juhos, Jack Brady, Matthias Bethge, Thadd\\\"aus Wiedemer, Wieland Brendel","submitted_at":"2023-10-09T01:18:07Z","abstract_excerpt":"Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely conjectured to enable compositional generalization. Yet, it remains unclear when this conjecture will be true, as a principled theoretical or empirical understanding of compositional generalization is lacking. In this work, we investigate when compositional generalization is guaranteed for object-centric representations through the lens of identifiability theory. W"},"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":"2310.05327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T01:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"3ed8e9525bb266fbf4d148d3331e83a411002cd27fe430a992d9a8ff15c9058f","abstract_canon_sha256":"c77b187449abdfe8dcf435f5592ec2060da4312f0003ce145148dd3cb8ad0c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:09.994265Z","signature_b64":"22pS9tB77HRXkTr/NPpgUeetDo/UbJT/eUd1+4WCXazieERgZbQVsaYCS29hnpivLY9ChZS+uShJXeNI0xjjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35a69195be1759507b261af0ff85c906563c7631b394de7067109137b7dc5525","last_reissued_at":"2026-07-05T09:34:09.993784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:09.993784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Compositional Generalization for Object-Centric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Panfilov, Attila Juhos, Jack Brady, Matthias Bethge, Thadd\\\"aus Wiedemer, Wieland Brendel","submitted_at":"2023-10-09T01:18:07Z","abstract_excerpt":"Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learning object-centric representations, which are widely conjectured to enable compositional generalization. Yet, it remains unclear when this conjecture will be true, as a principled theoretical or empirical understanding of compositional generalization is lacking. In this work, we investigate when compositional generalization is guaranteed for object-centric representations through the lens of identifiability theory. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05327","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/2310.05327/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":"2310.05327","created_at":"2026-07-05T09:34:09.993841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05327v2","created_at":"2026-07-05T09:34:09.993841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05327","created_at":"2026-07-05T09:34:09.993841+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWTJDFN6C5MV","created_at":"2026-07-05T09:34:09.993841+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWTJDFN6C5MVA6ZG","created_at":"2026-07-05T09:34:09.993841+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWTJDFN6","created_at":"2026-07-05T09:34:09.993841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":177,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15306","citing_title":"Generalization in LLM Problem Solving: The Case of the Shortest Path","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ","json":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ.json","graph_json":"https://pith.science/api/pith-number/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/graph.json","events_json":"https://pith.science/api/pith-number/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/events.json","paper":"https://pith.science/paper/GWTJDFN6"},"agent_actions":{"view_html":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ","download_json":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ.json","view_paper":"https://pith.science/paper/GWTJDFN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05327&json=true","fetch_graph":"https://pith.science/api/pith-number/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/action/storage_attestation","attest_author":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/action/author_attestation","sign_citation":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/action/citation_signature","submit_replication":"https://pith.science/pith/GWTJDFN6C5MVA6ZGDLYP7BOJAZ/action/replication_record"}},"created_at":"2026-07-05T09:34:09.993841+00:00","updated_at":"2026-07-05T09:34:09.993841+00:00"}