{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7IKPJQIXQX5NQM3TH3ZF2AA4VV","short_pith_number":"pith:7IKPJQIX","schema_version":"1.0","canonical_sha256":"fa14f4c11785fad833733ef25d001cad724e5211b8952341d0d9d6a8756365eb","source":{"kind":"arxiv","id":"2412.14957","version":2},"attestation_state":"computed","paper":{"title":"Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Andrii Zadaianchuk, Davide Allegro, Efstratios Gavves, Leonardo Barcellona, Samuele Papa, Stefano Ghidoni","submitted_at":"2024-12-19T15:38:15Z","abstract_excerpt":"A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot directly and explicitly imitate the actual environment in front of a robot, often resulting in unrealistic behaviors and hallucinations that make them unsuitable for real-world robotics applications. To overcome those challenges, we propose to rethink robot world models as learnable digital twins. We introduce DreMa, a new approach for constructing digital twins automatically using learned explicit representations of the "},"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":"2412.14957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-19T15:38:15Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b1e47cb9d156e786b9f6f96f5b3f02e84ae293e11b154686a6966af02a85d0d4","abstract_canon_sha256":"441280a3b2f97215079541ab3deb03e8c5bf088118bb97a6e29ed6bf0931bffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:22.332045Z","signature_b64":"aMqqdhROxC9LJ89eqErx8eEnXtjtvwYSqqgLUPF8ybC7IQNzu81nBLfcxC9waPZeYTh4bW1YowlkhljByApEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa14f4c11785fad833733ef25d001cad724e5211b8952341d0d9d6a8756365eb","last_reissued_at":"2026-07-05T10:27:22.329704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:22.329704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Andrii Zadaianchuk, Davide Allegro, Efstratios Gavves, Leonardo Barcellona, Samuele Papa, Stefano Ghidoni","submitted_at":"2024-12-19T15:38:15Z","abstract_excerpt":"A world model provides an agent with a representation of its environment, enabling it to predict the causal consequences of its actions. Current world models typically cannot directly and explicitly imitate the actual environment in front of a robot, often resulting in unrealistic behaviors and hallucinations that make them unsuitable for real-world robotics applications. To overcome those challenges, we propose to rethink robot world models as learnable digital twins. We introduce DreMa, a new approach for constructing digital twins automatically using learned explicit representations of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14957","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/2412.14957/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":"2412.14957","created_at":"2026-07-05T10:27:22.329816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14957v2","created_at":"2026-07-05T10:27:22.329816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14957","created_at":"2026-07-05T10:27:22.329816+00:00"},{"alias_kind":"pith_short_12","alias_value":"7IKPJQIXQX5N","created_at":"2026-07-05T10:27:22.329816+00:00"},{"alias_kind":"pith_short_16","alias_value":"7IKPJQIXQX5NQM3T","created_at":"2026-07-05T10:27:22.329816+00:00"},{"alias_kind":"pith_short_8","alias_value":"7IKPJQIX","created_at":"2026-07-05T10:27:22.329816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13053","citing_title":"EA-WM: Event-Aware World Models with Task-Specification Grounding for Long-Horizon Manipulation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10645","citing_title":"ManiSplat: Manipulation Trajectory Synthesis from Monocular Video via Decoupled 3D Gaussian Splatting","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30542","citing_title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":269,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25459","citing_title":"GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16592","citing_title":"Human Cognition in Machines: A Unified Perspective of World Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV","json":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV.json","graph_json":"https://pith.science/api/pith-number/7IKPJQIXQX5NQM3TH3ZF2AA4VV/graph.json","events_json":"https://pith.science/api/pith-number/7IKPJQIXQX5NQM3TH3ZF2AA4VV/events.json","paper":"https://pith.science/paper/7IKPJQIX"},"agent_actions":{"view_html":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV","download_json":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV.json","view_paper":"https://pith.science/paper/7IKPJQIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14957&json=true","fetch_graph":"https://pith.science/api/pith-number/7IKPJQIXQX5NQM3TH3ZF2AA4VV/graph.json","fetch_events":"https://pith.science/api/pith-number/7IKPJQIXQX5NQM3TH3ZF2AA4VV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV/action/storage_attestation","attest_author":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV/action/author_attestation","sign_citation":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV/action/citation_signature","submit_replication":"https://pith.science/pith/7IKPJQIXQX5NQM3TH3ZF2AA4VV/action/replication_record"}},"created_at":"2026-07-05T10:27:22.329816+00:00","updated_at":"2026-07-05T10:27:22.329816+00:00"}