{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C4FH2U6UFDVFQN6YB2TEXDTV6C","short_pith_number":"pith:C4FH2U6U","schema_version":"1.0","canonical_sha256":"170a7d53d428ea5837d80ea64b8e75f09e8b9c0340a1305cfbc14129937f9386","source":{"kind":"arxiv","id":"2402.03326","version":1},"attestation_state":"computed","paper":{"title":"Slot Structured World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aske Plaat, Jonathan Collu, Riccardo Majellaro, Thomas M. Moerland","submitted_at":"2024-01-08T21:19:30Z","abstract_excerpt":"The ability to perceive and reason about individual objects and their interactions is a goal to be achieved for building intelligent artificial systems. State-of-the-art approaches use a feedforward encoder to extract object embeddings and a latent graph neural network to model the interaction between these object embeddings. However, the feedforward encoder can not extract {\\it object-centric} representations, nor can it disentangle multiple objects with similar appearance. To solve these issues, we introduce {\\it Slot Structured World Models} (SSWM), a class of world models that combines an "},"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":"2402.03326","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-08T21:19:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1c1f5744d66a771d35481d2e05447745acf33c8d17082d9cc0a6ff843c11832d","abstract_canon_sha256":"aea087520de8ab76f84632aea66e0f77dfb4a3dfe6de44c7cedc42669f47a7c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:50.772024Z","signature_b64":"vdNxPDizeOad44Q20EWp64toZoo+n7b7AKtwFLtyCjbwTvGKzGnp/I4Q1vPcQu3KxiVEU9HNeM8CeSWPFm8GCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"170a7d53d428ea5837d80ea64b8e75f09e8b9c0340a1305cfbc14129937f9386","last_reissued_at":"2026-07-05T07:41:50.771594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:50.771594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Slot Structured World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aske Plaat, Jonathan Collu, Riccardo Majellaro, Thomas M. Moerland","submitted_at":"2024-01-08T21:19:30Z","abstract_excerpt":"The ability to perceive and reason about individual objects and their interactions is a goal to be achieved for building intelligent artificial systems. State-of-the-art approaches use a feedforward encoder to extract object embeddings and a latent graph neural network to model the interaction between these object embeddings. However, the feedforward encoder can not extract {\\it object-centric} representations, nor can it disentangle multiple objects with similar appearance. To solve these issues, we introduce {\\it Slot Structured World Models} (SSWM), a class of world models that combines an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03326","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/2402.03326/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":"2402.03326","created_at":"2026-07-05T07:41:50.771651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03326v1","created_at":"2026-07-05T07:41:50.771651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03326","created_at":"2026-07-05T07:41:50.771651+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4FH2U6UFDVF","created_at":"2026-07-05T07:41:50.771651+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4FH2U6UFDVFQN6Y","created_at":"2026-07-05T07:41:50.771651+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4FH2U6U","created_at":"2026-07-05T07:41:50.771651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08775","citing_title":"Unifying Object-Centric World Models and Diffusion Policy: A Hierarchical Framework for Multi-Stage Robotic Tasks","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C","json":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C.json","graph_json":"https://pith.science/api/pith-number/C4FH2U6UFDVFQN6YB2TEXDTV6C/graph.json","events_json":"https://pith.science/api/pith-number/C4FH2U6UFDVFQN6YB2TEXDTV6C/events.json","paper":"https://pith.science/paper/C4FH2U6U"},"agent_actions":{"view_html":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C","download_json":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C.json","view_paper":"https://pith.science/paper/C4FH2U6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03326&json=true","fetch_graph":"https://pith.science/api/pith-number/C4FH2U6UFDVFQN6YB2TEXDTV6C/graph.json","fetch_events":"https://pith.science/api/pith-number/C4FH2U6UFDVFQN6YB2TEXDTV6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C/action/storage_attestation","attest_author":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C/action/author_attestation","sign_citation":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C/action/citation_signature","submit_replication":"https://pith.science/pith/C4FH2U6UFDVFQN6YB2TEXDTV6C/action/replication_record"}},"created_at":"2026-07-05T07:41:50.771651+00:00","updated_at":"2026-07-05T07:41:50.771651+00:00"}