{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y3IAWQORQXQDPJATOGNIW7AKTF","short_pith_number":"pith:Y3IAWQOR","schema_version":"1.0","canonical_sha256":"c6d00b41d185e037a413719a8b7c0a9973e2a2f9cfae86de78ff5e943e7fcbd0","source":{"kind":"arxiv","id":"2410.08822","version":2},"attestation_state":"computed","paper":{"title":"SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Angel Villar-Corrales, Jan Niklas Ewertz, Malte Mosbach, Sven Behnke","submitted_at":"2024-10-11T14:03:31Z","abstract_excerpt":"Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency over model-free methods by learning from imagined rollouts. Furthermore, because the latent space serves as input to behavior models, the informative representations learned by the world model facilitate efficient learning of desired skills. Most existing methods rely on holistic representations of the environment's state. In contrast, humans reason about ob"},"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":"2410.08822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T14:03:31Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"062a07cadd53e0c21a0e325a981753d93f25e32cc0bbc262034fa0a76d6167c5","abstract_canon_sha256":"535baf919de0b893c57e659282926c28ebc30ea0dc43cd7bf8ea286b4fc850f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:44.843971Z","signature_b64":"25vxLKCmOq6U6btzHEr7Tsb35DUiyeEaiV0nk44F7GCM5eC2/v/zraY7/StfpDCyIRJj7eC/PB83b/DL/LxnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6d00b41d185e037a413719a8b7c0a9973e2a2f9cfae86de78ff5e943e7fcbd0","last_reissued_at":"2026-07-05T10:10:44.843555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:44.843555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Angel Villar-Corrales, Jan Niklas Ewertz, Malte Mosbach, Sven Behnke","submitted_at":"2024-10-11T14:03:31Z","abstract_excerpt":"Learning a latent dynamics model provides a task-agnostic representation of an agent's understanding of its environment. Leveraging this knowledge for model-based reinforcement learning (RL) holds the potential to improve sample efficiency over model-free methods by learning from imagined rollouts. Furthermore, because the latent space serves as input to behavior models, the informative representations learned by the world model facilitate efficient learning of desired skills. Most existing methods rely on holistic representations of the environment's state. In contrast, humans reason about ob"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08822","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/2410.08822/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":"2410.08822","created_at":"2026-07-05T10:10:44.843612+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.08822v2","created_at":"2026-07-05T10:10:44.843612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08822","created_at":"2026-07-05T10:10:44.843612+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3IAWQORQXQD","created_at":"2026-07-05T10:10:44.843612+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3IAWQORQXQDPJAT","created_at":"2026-07-05T10:10:44.843612+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3IAWQOR","created_at":"2026-07-05T10:10:44.843612+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06925","citing_title":"Grounding Spatial Relations in a Compact World Model: Instruction Leakage and a Goal-Free Dynamics Fix","ref_index":15,"is_internal_anchor":true},{"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":20,"is_internal_anchor":false},{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01950","citing_title":"TRAP: Tail-aware Ranking Attack for World-Model Planning","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF","json":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF.json","graph_json":"https://pith.science/api/pith-number/Y3IAWQORQXQDPJATOGNIW7AKTF/graph.json","events_json":"https://pith.science/api/pith-number/Y3IAWQORQXQDPJATOGNIW7AKTF/events.json","paper":"https://pith.science/paper/Y3IAWQOR"},"agent_actions":{"view_html":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF","download_json":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF.json","view_paper":"https://pith.science/paper/Y3IAWQOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.08822&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3IAWQORQXQDPJATOGNIW7AKTF/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3IAWQORQXQDPJATOGNIW7AKTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF/action/storage_attestation","attest_author":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF/action/author_attestation","sign_citation":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF/action/citation_signature","submit_replication":"https://pith.science/pith/Y3IAWQORQXQDPJATOGNIW7AKTF/action/replication_record"}},"created_at":"2026-07-05T10:10:44.843612+00:00","updated_at":"2026-07-05T10:10:44.843612+00:00"}